{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/instruction-following","name":"Instruction Following","slug":"instruction-following","description_markdown":"Instruction following is the basic task of the model. This task is dedicated to evaluating the ability of the large model to follow human instructions. It is hoped that the model can generate controllable and safe answers.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1135,"papers_with_code":609,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":14,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/instruction-following-on-ifeval","slug":"instruction-following-on-ifeval","dataset":"IFEval","dataset_url":"/dataset/ifeval","rows_in_archive":4,"metrics":["Inst-level loose-accuracy","Inst-level strict-accuracy","Prompt-level loose-accuracy","Prompt-level strict-accuracy"],"first_row_in_archive_order":{"model":"AutoIF (Llama3 70B)","paper_title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","paper_url":"/paper/self-play-with-execution-feedback-improving","paper_date":"2024-06-19","arxiv_id":"2406.13542","code_links":[{"title":"QwenLM/AutoIF","url":"https://github.com/QwenLM/AutoIF"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-play-with-execution-feedback-improving#ran","syntology_url":"https://syntology.ai/paper/2406.13542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13542"}},"official":{"repos":["QwenLM/AutoIF"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/ifeval","name":"IFEval","full_name":"Instruction Following Evaluation Datset","num_papers_in_archive":180},{"url":"/dataset/gscan","name":"GSCAN","full_name":"Grounded SCAN","num_papers_in_archive":22},{"url":"/dataset/mimic-it","name":"MIMIC-IT","full_name":"","num_papers_in_archive":11},{"url":"/dataset/ugif","name":"UGIF","full_name":"","num_papers_in_archive":10},{"url":"/dataset/bactrian-x","name":"Bactrian-X","full_name":"","num_papers_in_archive":9},{"url":"/dataset/cidar","name":"CIDAR","full_name":"","num_papers_in_archive":4},{"url":"/dataset/alpaca-data-galician","name":"Alpaca Data Galician","full_name":"Alpaca Data Galician","num_papers_in_archive":1},{"url":"/dataset/instructopenwiki","name":"InstructOpenWiki","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sequential-instructions","name":"Sequential Instructions","full_name":"","num_papers_in_archive":1},{"url":"/dataset/surgeglobal-evol-instruct","name":"SurgeGlobal/Evol-Instruct","full_name":"","num_papers_in_archive":1},{"url":"/dataset/surgeglobal-lamini","name":"SurgeGlobal/LaMini","full_name":"","num_papers_in_archive":1},{"url":"/dataset/surgeglobal-orca","name":"SurgeGlobal/Orca","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tamil-alpaca","name":"Tamil Alpaca","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tamil-alpaca-orca","name":"Tamil Alpaca Orca","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/visual-instruction-following","name":"visual instruction following"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":12,"rows_per_page":100,"shown":100,"of":1135,"of_with_code":609,"tagged_in_all":1135,"counts":{"archive_papers_tagged":1135,"with_a_code_link":609,"where_syntology_ran_a_sample":311,"not_listed_spam_title":0,"listed":1135,"listed_where_code_ran":311,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":243,"every_run_a_failure_of_syntologys_instrument":68,"listed_with_a_run_with_no_instrument_failure":243,"listed_every_run_a_failure_of_syntologys_instrument":68,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/qlora-efficient-finetuning-of-quantized-llms","slug":"qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","repositories_listed":20,"syntology":{"n":26,"n_ran":18,"n_constructed":1,"n_ran_checked":6,"n_instrument":12,"n_unverified":8,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/qlora-efficient-finetuning-of-quantized-llms#ran","syntology_url":"https://syntology.ai/paper/2305.14314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14314"}},"official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official","unlocated"]}}},{"url":"/paper/self-instruct-aligning-language-model-with","slug":"self-instruct-aligning-language-model-with","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","date":"2022-12-20","arxiv_id":"2212.10560","repositories_listed":19,"syntology":{"n":17,"n_ran":10,"n_constructed":3,"n_ran_checked":6,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/self-instruct-aligning-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2212.10560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10560"}},"official":{"repos":["tatsu-lab/stanford_alpaca","yizhongw/self-instruct"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_constructed":6,"n_ran_checked":8,"n_instrument":8,"n_unverified":35,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]}}},{"url":"/paper/habitat-a-platform-for-embodied-ai-research","slug":"habitat-a-platform-for-embodied-ai-research","title":"Habitat: A Platform for Embodied AI Research","date":"2019-04-02","arxiv_id":"1904.01201","repositories_listed":13,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/habitat-a-platform-for-embodied-ai-research#ran","syntology_url":"https://syntology.ai/paper/1904.01201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01201"}},"official":{"repos":["facebookresearch/habitat-sim"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/benchmarking-generalization-via-in-context","slug":"benchmarking-generalization-via-in-context","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","date":"2022-04-16","arxiv_id":"2204.07705","repositories_listed":10,"syntology":{"n":28,"n_ran":17,"n_constructed":1,"n_ran_checked":15,"n_instrument":2,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":4,"phrase":"17 ran (of which 1 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/benchmarking-generalization-via-in-context#ran","syntology_url":"https://syntology.ai/paper/2204.07705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07705"}},"official":{"repos":["allenai/natural-instructions"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/chatglm-a-family-of-large-language-models","slug":"chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","arxiv_id":"2406.12793","repositories_listed":7,"syntology":{"n":29,"n_ran":21,"n_constructed":0,"n_ran_checked":15,"n_instrument":6,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/chatglm-a-family-of-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2406.12793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12793"}},"official":{"repos":["thudm/chatglm-6b"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/llama-adapter-efficient-fine-tuning-of","slug":"llama-adapter-efficient-fine-tuning-of","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","date":"2023-03-28","arxiv_id":"2303.16199","repositories_listed":7,"syntology":null},{"url":"/paper/qwen2-5-technical-report","slug":"qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qwen2-5-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.15115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15115"}},"official":{"repos":["qwenlm/qwen2.5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/distillm-towards-streamlined-distillation-for","slug":"distillm-towards-streamlined-distillation-for","title":"DistiLLM: Towards Streamlined Distillation for Large Language Models","date":"2024-02-06","arxiv_id":"2402.03898","repositories_listed":5,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distillm-towards-streamlined-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2402.03898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03898"}},"official":{"repos":["jongwooko/distillm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/lmsys-chat-1m-a-large-scale-real-world-llm","slug":"lmsys-chat-1m-a-large-scale-real-world-llm","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","date":"2023-09-21","arxiv_id":"2309.11998","repositories_listed":5,"syntology":null},{"url":"/paper/point-bind-point-llm-aligning-point-cloud","slug":"point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","arxiv_id":"2309.00615","repositories_listed":5,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":5,"n_pointer_only":15,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/point-bind-point-llm-aligning-point-cloud#ran","syntology_url":"https://syntology.ai/paper/2309.00615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00615"}},"official":{"repos":["ziyuguo99/point-bind_point-llm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mapping-instructions-to-actions-in-3d","slug":"mapping-instructions-to-actions-in-3d","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","date":"2018-09-04","arxiv_id":"1809.00786","repositories_listed":5,"syntology":null},{"url":"/paper/instruction-following-evaluation-for-large","slug":"instruction-following-evaluation-for-large","title":"Instruction-Following Evaluation for Large Language Models","date":"2023-11-14","arxiv_id":"2311.07911","repositories_listed":4,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/instruction-following-evaluation-for-large#ran","syntology_url":"https://syntology.ai/paper/2311.07911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07911"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/longlora-efficient-fine-tuning-of-long","slug":"longlora-efficient-fine-tuning-of-long","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","date":"2023-09-21","arxiv_id":"2309.12307","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/longlora-efficient-fine-tuning-of-long#ran","syntology_url":"https://syntology.ai/paper/2309.12307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12307"}},"official":{"repos":["dvlab-research/longlora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/how-far-can-camels-go-exploring-the-state-of","slug":"how-far-can-camels-go-exploring-the-state-of","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","date":"2023-06-07","arxiv_id":"2306.04751","repositories_listed":4,"syntology":{"n":12,"n_ran":6,"n_constructed":1,"n_ran_checked":2,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/how-far-can-camels-go-exploring-the-state-of#ran","syntology_url":"https://syntology.ai/paper/2306.04751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04751"}},"official":{"repos":["allenai/open-instruct"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/wizardlm-empowering-large-language-models-to","slug":"wizardlm-empowering-large-language-models-to","title":"WizardLM: Empowering Large Language Models to Follow Complex Instructions","date":"2023-04-24","arxiv_id":"2304.12244","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/wizardlm-empowering-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2304.12244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.12244"}},"official":{"repos":["nlpxucan/wizardlm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/fusechat-knowledge-fusion-of-chat-models-1","slug":"fusechat-knowledge-fusion-of-chat-models-1","title":"FuseChat: Knowledge Fusion of Chat Models","date":"2024-08-15","arxiv_id":"2408.07990","repositories_listed":3,"syntology":null},{"url":"/paper/funaudiollm-voice-understanding-and","slug":"funaudiollm-voice-understanding-and","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","date":"2024-07-04","arxiv_id":"2407.04051","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/funaudiollm-voice-understanding-and#ran","syntology_url":"https://syntology.ai/paper/2407.04051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04051"}},"official":{"repos":["FunAudioLLM/SenseVoice","funaudiollm/cosyvoice"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ruler-improving-llm-controllability-by-rule","slug":"ruler-improving-llm-controllability-by-rule","title":"RuleR: Improving LLM Controllability by Rule-based Data Recycling","date":"2024-06-22","arxiv_id":"2406.15938","repositories_listed":3,"syntology":null},{"url":"/paper/mosaic-it-enhancing-instruction-tuning-with","slug":"mosaic-it-enhancing-instruction-tuning-with","title":"Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning","date":"2024-05-22","arxiv_id":"2405.13326","repositories_listed":3,"syntology":null},{"url":"/paper/shapellm-universal-3d-object-understanding","slug":"shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","date":"2024-02-27","arxiv_id":"2402.17766","repositories_listed":3,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":6,"n_instrument":8,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/shapellm-universal-3d-object-understanding#ran","syntology_url":"https://syntology.ai/paper/2402.17766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17766"}},"official":{"repos":["qizekun/ShapeLLM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/language-models-are-homer-simpson-safety-re","slug":"language-models-are-homer-simpson-safety-re","title":"Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic","date":"2024-02-19","arxiv_id":"2402.11746","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":2,"n_instrument":11,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":9,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/language-models-are-homer-simpson-safety-re#ran","syntology_url":"https://syntology.ai/paper/2402.11746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11746"}},"official":{"repos":["declare-lab/resta","hiyouga/llama-factory"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/openfedllm-training-large-language-models-on","slug":"openfedllm-training-large-language-models-on","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","date":"2024-02-10","arxiv_id":"2402.06954","repositories_listed":3,"syntology":null},{"url":"/paper/self-rewarding-language-models","slug":"self-rewarding-language-models","title":"Self-Rewarding Language Models","date":"2024-01-18","arxiv_id":"2401.10020","repositories_listed":3,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/self-rewarding-language-models#ran","syntology_url":"https://syntology.ai/paper/2401.10020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10020"}},"official":null}},{"url":"/paper/waterbench-towards-holistic-evaluation-of","slug":"waterbench-towards-holistic-evaluation-of","title":"WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models","date":"2023-11-13","arxiv_id":"2311.07138","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/waterbench-towards-holistic-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2311.07138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07138"}},"official":{"repos":["THU-KEG/WaterBench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/language-models-are-super-mario-absorbing","slug":"language-models-are-super-mario-absorbing","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","date":"2023-11-06","arxiv_id":"2311.03099","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-are-super-mario-absorbing#ran","syntology_url":"https://syntology.ai/paper/2311.03099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03099"}},"official":{"repos":["yule-buaa/mergelm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/modulora-finetuning-3-bit-llms-on-consumer","slug":"modulora-finetuning-3-bit-llms-on-consumer","title":"ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers","date":"2023-09-28","arxiv_id":"2309.16119","repositories_listed":3,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/modulora-finetuning-3-bit-llms-on-consumer#ran","syntology_url":"https://syntology.ai/paper/2309.16119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16119"}},"official":{"repos":["kuleshov-group/llmtools","kuleshov-group/modulora-experiment"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/from-quantity-to-quality-boosting-llm","slug":"from-quantity-to-quality-boosting-llm","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","date":"2023-08-23","arxiv_id":"2308.12032","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-quantity-to-quality-boosting-llm#ran","syntology_url":"https://syntology.ai/paper/2308.12032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12032"}},"official":{"repos":["mingliiii/cherry_llm","tianyi-lab/cherry_llm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/instructiongpt-4-a-200-instruction-paradigm","slug":"instructiongpt-4-a-200-instruction-paradigm","title":"InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4","date":"2023-08-23","arxiv_id":"2308.12067","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/instructiongpt-4-a-200-instruction-paradigm#ran","syntology_url":"https://syntology.ai/paper/2308.12067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12067"}},"official":{"repos":["waltonfuture/InstructionGPT-4"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/l-eval-instituting-standardized-evaluation","slug":"l-eval-instituting-standardized-evaluation","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","date":"2023-07-20","arxiv_id":"2307.11088","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/l-eval-instituting-standardized-evaluation#ran","syntology_url":"https://syntology.ai/paper/2307.11088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11088"}},"official":{"repos":["openlmlab/leval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/alpagasus-training-a-better-alpaca-with-fewer","slug":"alpagasus-training-a-better-alpaca-with-fewer","title":"AlpaGasus: Training A Better Alpaca with Fewer Data","date":"2023-07-17","arxiv_id":"2307.08701","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alpagasus-training-a-better-alpaca-with-fewer#ran","syntology_url":"https://syntology.ai/paper/2307.08701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08701"}},"official":{"repos":["gpt4life/alpagasus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mmbench-is-your-multi-modal-model-an-all","slug":"mmbench-is-your-multi-modal-model-an-all","title":"MMBench: Is Your Multi-modal Model an All-around Player?","date":"2023-07-12","arxiv_id":"2307.06281","repositories_listed":3,"syntology":null},{"url":"/paper/shifting-attention-to-relevance-towards-the","slug":"shifting-attention-to-relevance-towards-the","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","date":"2023-07-03","arxiv_id":"2307.01379","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shifting-attention-to-relevance-towards-the#ran","syntology_url":"https://syntology.ai/paper/2307.01379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01379"}},"official":{"repos":["jinhaoduan/sar","jinhaoduan/shifting-attention-to-relevance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llama-adapter-v2-parameter-efficient-visual","slug":"llama-adapter-v2-parameter-efficient-visual","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","date":"2023-04-28","arxiv_id":"2304.15010","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/llama-adapter-v2-parameter-efficient-visual#ran","syntology_url":"https://syntology.ai/paper/2304.15010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.15010"}},"official":{"repos":["zrrskywalker/llama-adapter"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/camel-communicative-agents-for-mind","slug":"camel-communicative-agents-for-mind","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","date":"2023-03-31","arxiv_id":"2303.17760","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/camel-communicative-agents-for-mind#ran","syntology_url":"https://syntology.ai/paper/2303.17760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17760"}},"official":{"repos":["camel-ai/camel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/precise-zero-shot-dense-retrieval-without","slug":"precise-zero-shot-dense-retrieval-without","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","date":"2022-12-20","arxiv_id":"2212.10496","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/precise-zero-shot-dense-retrieval-without#ran","syntology_url":"https://syntology.ai/paper/2212.10496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10496"}},"official":{"repos":["texttron/hyde"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/desta2-5-audio-toward-general-purpose-large","slug":"desta2-5-audio-toward-general-purpose-large","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","date":"2025-07-03","arxiv_id":"2507.02768","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/desta2-5-audio-toward-general-purpose-large#ran","syntology_url":"https://syntology.ai/paper/2507.02768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.02768"}},"official":{"repos":["kehanlu/desta2.5-audio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llama-omni2-llm-based-real-time-spoken","slug":"llama-omni2-llm-based-real-time-spoken","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","date":"2025-05-05","arxiv_id":"2505.02625","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":3,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llama-omni2-llm-based-real-time-spoken#ran","syntology_url":"https://syntology.ai/paper/2505.02625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02625"}},"official":{"repos":["ictnlp/llama-omni2"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed"]}}},{"url":"/paper/how-instruction-and-reasoning-data-shape-post","slug":"how-instruction-and-reasoning-data-shape-post","title":"How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients","date":"2025-04-14","arxiv_id":"2504.10766","repositories_listed":2,"syntology":null},{"url":"/paper/vargpt-v1-1-improve-visual-autoregressive","slug":"vargpt-v1-1-improve-visual-autoregressive","title":"VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning","date":"2025-04-03","arxiv_id":"2504.02949","repositories_listed":2,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/vargpt-v1-1-improve-visual-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2504.02949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02949"}},"official":{"repos":["vargpt-family/vargpt-v1.1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/textgames-learning-to-self-play-text-based","slug":"textgames-learning-to-self-play-text-based","title":"TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning","date":"2025-02-25","arxiv_id":"2502.18431","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/textgames-learning-to-self-play-text-based#ran","syntology_url":"https://syntology.ai/paper/2502.18431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18431"}},"official":{"repos":["fhudi/textgames"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/large-language-diffusion-models","slug":"large-language-diffusion-models","title":"Large Language Diffusion Models","date":"2025-02-14","arxiv_id":"2502.09992","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-language-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2502.09992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.09992"}},"official":null}},{"url":"/paper/vargpt-unified-understanding-and-generation","slug":"vargpt-unified-understanding-and-generation","title":"VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model","date":"2025-01-21","arxiv_id":"2501.12327","repositories_listed":2,"syntology":null},{"url":"/paper/codeplan-unlocking-reasoning-potential-in","slug":"codeplan-unlocking-reasoning-potential-in","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","date":"2024-09-19","arxiv_id":"2409.12452","repositories_listed":2,"syntology":null},{"url":"/paper/spinning-the-golden-thread-benchmarking-long","slug":"spinning-the-golden-thread-benchmarking-long","title":"LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs","date":"2024-09-03","arxiv_id":"2409.02076","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spinning-the-golden-thread-benchmarking-long#ran","syntology_url":"https://syntology.ai/paper/2409.02076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02076"}},"official":{"repos":["mozhu621/SGT","mozhu621/longgenbench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/jamba-1-5-hybrid-transformer-mamba-models-at","slug":"jamba-1-5-hybrid-transformer-mamba-models-at","title":"Jamba-1.5: Hybrid Transformer-Mamba Models at Scale","date":"2024-08-22","arxiv_id":"2408.12570","repositories_listed":2,"syntology":null},{"url":"/paper/seallms-3-open-foundation-and-chat","slug":"seallms-3-open-foundation-and-chat","title":"SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages","date":"2024-07-29","arxiv_id":"2407.19672","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/seallms-3-open-foundation-and-chat#ran","syntology_url":"https://syntology.ai/paper/2407.19672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19672"}},"official":{"repos":["DAMO-NLP-SG/SeaExam"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/qwen2-audio-technical-report","slug":"qwen2-audio-technical-report","title":"Qwen2-Audio Technical Report","date":"2024-07-15","arxiv_id":"2407.10759","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qwen2-audio-technical-report#ran","syntology_url":"https://syntology.ai/paper/2407.10759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10759"}},"official":{"repos":["qwenlm/qwen2-audio"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mm-instruct-generated-visual-instructions-for","slug":"mm-instruct-generated-visual-instructions-for","title":"MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment","date":"2024-06-28","arxiv_id":"2406.19736","repositories_listed":2,"syntology":null},{"url":"/paper/snap-unlearning-selective-knowledge-in-large","slug":"snap-unlearning-selective-knowledge-in-large","title":"Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport","date":"2024-06-18","arxiv_id":"2406.12329","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/snap-unlearning-selective-knowledge-in-large#ran","syntology_url":"https://syntology.ai/paper/2406.12329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12329"}},"official":{"repos":["brightjade/Opt-Out","brightjade/snap-unlearning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/gama-a-large-audio-language-model-with","slug":"gama-a-large-audio-language-model-with","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","date":"2024-06-17","arxiv_id":"2406.11768","repositories_listed":2,"syntology":null},{"url":"/paper/unpacking-dpo-and-ppo-disentangling-best","slug":"unpacking-dpo-and-ppo-disentangling-best","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","date":"2024-06-13","arxiv_id":"2406.09279","repositories_listed":2,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":2,"n_instrument":13,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 13 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/unpacking-dpo-and-ppo-disentangling-best#ran","syntology_url":"https://syntology.ai/paper/2406.09279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09279"}},"official":{"repos":["allenai/open-instruct","hamishivi/easylm"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/f-lmm-grounding-frozen-large-multimodal","slug":"f-lmm-grounding-frozen-large-multimodal","title":"F-LMM: Grounding Frozen Large Multimodal Models","date":"2024-06-09","arxiv_id":"2406.05821","repositories_listed":2,"syntology":null},{"url":"/paper/the-biggen-bench-a-principled-benchmark-for","slug":"the-biggen-bench-a-principled-benchmark-for","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","date":"2024-06-09","arxiv_id":"2406.05761","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-biggen-bench-a-principled-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2406.05761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05761"}},"official":{"repos":["prometheus-eval/prometheus-eval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/alchemistcoder-harmonizing-and-eliciting-code","slug":"alchemistcoder-harmonizing-and-eliciting-code","title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data","date":"2024-05-29","arxiv_id":"2405.19265","repositories_listed":2,"syntology":null},{"url":"/paper/simpo-simple-preference-optimization-with-a","slug":"simpo-simple-preference-optimization-with-a","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","date":"2024-05-23","arxiv_id":"2405.14734","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simpo-simple-preference-optimization-with-a#ran","syntology_url":"https://syntology.ai/paper/2405.14734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14734"}},"official":{"repos":["princeton-nlp/simpo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rewardbench-evaluating-reward-models-for","slug":"rewardbench-evaluating-reward-models-for","title":"RewardBench: Evaluating Reward Models for Language Modeling","date":"2024-03-20","arxiv_id":"2403.13787","repositories_listed":2,"syntology":null},{"url":"/paper/aligners-decoupling-llms-and-alignment","slug":"aligners-decoupling-llms-and-alignment","title":"Aligners: Decoupling LLMs and Alignment","date":"2024-03-07","arxiv_id":"2403.04224","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligners-decoupling-llms-and-alignment#ran","syntology_url":"https://syntology.ai/paper/2403.04224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04224"}},"official":{"repos":["lilianngweta/aligners-and-inspectors","lilianngweta/aligners"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-preference-alignment-remedies","slug":"multi-modal-preference-alignment-remedies","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","date":"2024-02-16","arxiv_id":"2402.10884","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-modal-preference-alignment-remedies#ran","syntology_url":"https://syntology.ai/paper/2402.10884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10884"}},"official":{"repos":["findalexli/mllm-dpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/selective-reflection-tuning-student-selected","slug":"selective-reflection-tuning-student-selected","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","date":"2024-02-15","arxiv_id":"2402.10110","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selective-reflection-tuning-student-selected#ran","syntology_url":"https://syntology.ai/paper/2402.10110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10110"}},"official":{"repos":["tianyi-lab/reflection_tuning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/f-eval-asssessing-fundamental-abilities-with","slug":"f-eval-asssessing-fundamental-abilities-with","title":"F-Eval: Assessing Fundamental Abilities with Refined Evaluation Methods","date":"2024-01-26","arxiv_id":"2401.14869","repositories_listed":2,"syntology":null},{"url":"/paper/solar-10-7b-scaling-large-language-models","slug":"solar-10-7b-scaling-large-language-models","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","date":"2023-12-23","arxiv_id":"2312.15166","repositories_listed":2,"syntology":{"n":26,"n_ran":22,"n_constructed":0,"n_ran_checked":10,"n_instrument":12,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/solar-10-7b-scaling-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2312.15166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15166"}},"official":null}},{"url":"/paper/t-eval-evaluating-the-tool-utilization","slug":"t-eval-evaluating-the-tool-utilization","title":"T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step","date":"2023-12-21","arxiv_id":"2312.14033","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/t-eval-evaluating-the-tool-utilization#ran","syntology_url":"https://syntology.ai/paper/2312.14033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14033"}},"official":{"repos":["open-compass/t-eval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/m3dbench-let-s-instruct-large-models-with","slug":"m3dbench-let-s-instruct-large-models-with","title":"M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts","date":"2023-12-17","arxiv_id":"2312.10763","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3dbench-let-s-instruct-large-models-with#ran","syntology_url":"https://syntology.ai/paper/2312.10763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10763"}},"official":{"repos":["OpenM3D/M3DBench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lmdrive-closed-loop-end-to-end-driving-with","slug":"lmdrive-closed-loop-end-to-end-driving-with","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","date":"2023-12-12","arxiv_id":"2312.07488","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lmdrive-closed-loop-end-to-end-driving-with#ran","syntology_url":"https://syntology.ai/paper/2312.07488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07488"}},"official":{"repos":["opendilab/lmdrive"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/localized-symbolic-knowledge-distillation-for-1","slug":"localized-symbolic-knowledge-distillation-for-1","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","date":"2023-12-08","arxiv_id":"2312.04837","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/localized-symbolic-knowledge-distillation-for-1#ran","syntology_url":"https://syntology.ai/paper/2312.04837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04837"}},"official":{"repos":["jamespark3922/localized-skd","jamespark3922/lskd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/seallms-large-language-models-for-southeast","slug":"seallms-large-language-models-for-southeast","title":"SeaLLMs -- Large Language Models for Southeast Asia","date":"2023-12-01","arxiv_id":"2312.00738","repositories_listed":2,"syntology":null},{"url":"/paper/automatic-instruction-optimization-for-open","slug":"automatic-instruction-optimization-for-open","title":"CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning","date":"2023-11-22","arxiv_id":"2311.13246","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/automatic-instruction-optimization-for-open#ran","syntology_url":"https://syntology.ai/paper/2311.13246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13246"}},"official":{"repos":["lunyiliu/coachlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-medical-text-evaluation-with-gpt-4","slug":"enhancing-medical-text-evaluation-with-gpt-4","title":"DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation","date":"2023-11-16","arxiv_id":"2311.09581","repositories_listed":2,"syntology":null},{"url":"/paper/qwen-audio-advancing-universal-audio","slug":"qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","arxiv_id":"2311.07919","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}},"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/to-see-is-to-believe-prompting-gpt-4v-for","slug":"to-see-is-to-believe-prompting-gpt-4v-for","title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","date":"2023-11-13","arxiv_id":"2311.07574","repositories_listed":2,"syntology":null},{"url":"/paper/infmllm-a-unified-framework-for-visual","slug":"infmllm-a-unified-framework-for-visual","title":"InfMLLM: A Unified Framework for Visual-Language Tasks","date":"2023-11-12","arxiv_id":"2311.06791","repositories_listed":2,"syntology":null},{"url":"/paper/how-abilities-in-large-language-models-are","slug":"how-abilities-in-large-language-models-are","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","date":"2023-10-09","arxiv_id":"2310.05492","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-abilities-in-large-language-models-are#ran","syntology_url":"https://syntology.ai/paper/2310.05492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05492"}},"official":{"repos":["ofa-sys/gsm8k-screl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/chat-vector-a-simple-approach-to-equip-llms","slug":"chat-vector-a-simple-approach-to-equip-llms","title":"Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages","date":"2023-10-07","arxiv_id":"2310.04799","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/chat-vector-a-simple-approach-to-equip-llms#ran","syntology_url":"https://syntology.ai/paper/2310.04799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04799"}},"official":null}},{"url":"/paper/reformulating-vision-language-foundation","slug":"reformulating-vision-language-foundation","title":"Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants","date":"2023-10-01","arxiv_id":"2310.00653","repositories_listed":2,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":7,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 2 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reformulating-vision-language-foundation#ran","syntology_url":"https://syntology.ai/paper/2310.00653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00653"}},"official":{"repos":["thunlp/muffin"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mentalllama-interpretable-mental-health","slug":"mentalllama-interpretable-mental-health","title":"MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models","date":"2023-09-24","arxiv_id":"2309.13567","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mentalllama-interpretable-mental-health#ran","syntology_url":"https://syntology.ai/paper/2309.13567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13567"}},"official":{"repos":["stevekgyang/mentallama","stevekgyang/mentalllama"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/imagebind-llm-multi-modality-instruction","slug":"imagebind-llm-multi-modality-instruction","title":"ImageBind-LLM: Multi-modality Instruction Tuning","date":"2023-09-07","arxiv_id":"2309.03905","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/imagebind-llm-multi-modality-instruction#ran","syntology_url":"https://syntology.ai/paper/2309.03905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03905"}},"official":{"repos":["opengvlab/llama-adapter"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/code-llama-open-foundation-models-for-code","slug":"code-llama-open-foundation-models-for-code","title":"Code Llama: Open Foundation Models for Code","date":"2023-08-24","arxiv_id":"2308.12950","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/code-llama-open-foundation-models-for-code#ran","syntology_url":"https://syntology.ai/paper/2308.12950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12950"}},"official":{"repos":["facebookresearch/codellama"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/do-you-really-follow-me-adversarial","slug":"do-you-really-follow-me-adversarial","title":"Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection","date":"2023-08-17","arxiv_id":"2308.10819","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/do-you-really-follow-me-adversarial#ran","syntology_url":"https://syntology.ai/paper/2308.10819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10819"}},"official":{"repos":["leezekun/adv-instruct-eval","leezekun/instruction-following-robustness-eval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-alignment-with-instruction","slug":"self-alignment-with-instruction","title":"Self-Alignment with Instruction Backtranslation","date":"2023-08-11","arxiv_id":"2308.06259","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-alignment-with-instruction#ran","syntology_url":"https://syntology.ai/paper/2308.06259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06259"}},"official":null}},{"url":"/paper/what-matters-in-training-a-gpt4-style","slug":"what-matters-in-training-a-gpt4-style","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","date":"2023-07-05","arxiv_id":"2307.02469","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/what-matters-in-training-a-gpt4-style#ran","syntology_url":"https://syntology.ai/paper/2307.02469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02469"}},"official":null}},{"url":"/paper/llavar-enhanced-visual-instruction-tuning-for","slug":"llavar-enhanced-visual-instruction-tuning-for","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","date":"2023-06-29","arxiv_id":"2306.17107","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llavar-enhanced-visual-instruction-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2306.17107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17107"}},"official":{"repos":["SALT-NLP/LLaVAR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/knowledge-distillation-of-large-language","slug":"knowledge-distillation-of-large-language","title":"MiniLLM: Knowledge Distillation of Large Language Models","date":"2023-06-14","arxiv_id":"2306.08543","repositories_listed":2,"syntology":null},{"url":"/paper/navgpt-explicit-reasoning-in-vision-and","slug":"navgpt-explicit-reasoning-in-vision-and","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","date":"2023-05-26","arxiv_id":"2305.16986","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/navgpt-explicit-reasoning-in-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.16986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16986"}},"official":{"repos":["gengzezhou/navgpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/expertprompting-instructing-large-language","slug":"expertprompting-instructing-large-language","title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts","date":"2023-05-24","arxiv_id":"2305.14688","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/expertprompting-instructing-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14688"}},"official":{"repos":["ofa-sys/expertllama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/alpacafarm-a-simulation-framework-for-methods-1","slug":"alpacafarm-a-simulation-framework-for-methods-1","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","date":"2023-05-22","arxiv_id":"2305.14387","repositories_listed":2,"syntology":null},{"url":"/paper/x-llm-bootstrapping-advanced-large-language","slug":"x-llm-bootstrapping-advanced-large-language","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","date":"2023-05-07","arxiv_id":"2305.04160","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/x-llm-bootstrapping-advanced-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.04160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04160"}},"official":null}},{"url":"/paper/towards-better-instruction-following-language","slug":"towards-better-instruction-following-language","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","date":"2023-04-16","arxiv_id":"2304.07854","repositories_listed":2,"syntology":null},{"url":"/paper/instruction-tuning-with-gpt-4","slug":"instruction-tuning-with-gpt-4","title":"Instruction Tuning with GPT-4","date":"2023-04-06","arxiv_id":"2304.03277","repositories_listed":2,"syntology":null},{"url":"/paper/in-context-instruction-learning","slug":"in-context-instruction-learning","title":"Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following","date":"2023-02-28","arxiv_id":"2302.14691","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/in-context-instruction-learning#ran","syntology_url":"https://syntology.ai/paper/2302.14691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.14691"}},"official":{"repos":["seonghyeonye/icil","seonghyeonye/tapp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/more-than-you-ve-asked-for-a-comprehensive","slug":"more-than-you-ve-asked-for-a-comprehensive","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","date":"2023-02-23","arxiv_id":"2302.12173","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/more-than-you-ve-asked-for-a-comprehensive#ran","syntology_url":"https://syntology.ai/paper/2302.12173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12173"}},"official":{"repos":["greshake/llm-security","greshake/lm-safety"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/combining-modular-skills-in-multitask","slug":"combining-modular-skills-in-multitask","title":"Combining Modular Skills in Multitask Learning","date":"2022-02-28","arxiv_id":"2202.13914","repositories_listed":2,"syntology":null},{"url":"/paper/dialfred-dialogue-enabled-agents-for-embodied","slug":"dialfred-dialogue-enabled-agents-for-embodied","title":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","date":"2022-02-27","arxiv_id":"2202.13330","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dialfred-dialogue-enabled-agents-for-embodied#ran","syntology_url":"https://syntology.ai/paper/2202.13330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13330"}},"official":{"repos":["anonrabit/dialfred","xfgao/dialfred"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/guiding-multi-step-rearrangement-tasks-with","slug":"guiding-multi-step-rearrangement-tasks-with","title":"Guiding Multi-Step Rearrangement Tasks with Natural Language Instructions","date":"2021-11-08","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/language-as-an-abstraction-for-hierarchical","slug":"language-as-an-abstraction-for-hierarchical","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","date":"2019-06-18","arxiv_id":"1906.07343","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-as-an-abstraction-for-hierarchical#ran","syntology_url":"https://syntology.ai/paper/1906.07343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.07343"}},"official":{"repos":["google-research/clevr_robot_env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-replica-dataset-a-digital-replica-of","slug":"the-replica-dataset-a-digital-replica-of","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","date":"2019-06-13","arxiv_id":"1906.05797","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-follow-directions-in-street-view","slug":"learning-to-follow-directions-in-street-view","title":"Learning To Follow Directions in Street View","date":"2019-03-01","arxiv_id":"1903.00401","repositories_listed":2,"syntology":null},{"url":"/paper/drafterbench-benchmarking-large-language","slug":"drafterbench-benchmarking-large-language","title":"DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering","date":"2025-07-15","arxiv_id":"2507.11527","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/drafterbench-benchmarking-large-language#ran","syntology_url":"https://syntology.ai/paper/2507.11527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.11527"}},"official":{"repos":["eason-li-ais/drafterbench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-secalign-a-secure-foundation-llm-against","slug":"meta-secalign-a-secure-foundation-llm-against","title":"Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks","date":"2025-07-03","arxiv_id":"2507.02735","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-secalign-a-secure-foundation-llm-against#ran","syntology_url":"https://syntology.ai/paper/2507.02735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.02735"}},"official":{"repos":["facebookresearch/meta_secalign"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"syntology_records":70,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":9,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/instruction-following-on-ifeval","since_archive":"/sota/instruction-following-on-ifeval#since-judged","papers_judged":9,"placed":0}]},"papers_where_code_ran":311,"papers_where_code_ran_first_page":"/task/instruction-following/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":12,"url":"/task/instruction-following/papers/2","json":"/task/instruction-following/papers/2.json","rows":100},{"order":"archive","page":3,"of":12,"url":"/task/instruction-following/papers/3","json":"/task/instruction-following/papers/3.json","rows":100},{"order":"archive","page":4,"of":12,"url":"/task/instruction-following/papers/4","json":"/task/instruction-following/papers/4.json","rows":100},{"order":"archive","page":5,"of":12,"url":"/task/instruction-following/papers/5","json":"/task/instruction-following/papers/5.json","rows":100},{"order":"archive","page":6,"of":12,"url":"/task/instruction-following/papers/6","json":"/task/instruction-following/papers/6.json","rows":100},{"order":"archive","page":7,"of":12,"url":"/task/instruction-following/papers/7","json":"/task/instruction-following/papers/7.json","rows":100},{"order":"archive","page":8,"of":12,"url":"/task/instruction-following/papers/8","json":"/task/instruction-following/papers/8.json","rows":100},{"order":"archive","page":9,"of":12,"url":"/task/instruction-following/papers/9","json":"/task/instruction-following/papers/9.json","rows":100},{"order":"archive","page":10,"of":12,"url":"/task/instruction-following/papers/10","json":"/task/instruction-following/papers/10.json","rows":100},{"order":"archive","page":11,"of":12,"url":"/task/instruction-following/papers/11","json":"/task/instruction-following/papers/11.json","rows":100},{"order":"archive","page":12,"of":12,"url":"/task/instruction-following/papers/12","json":"/task/instruction-following/papers/12.json","rows":35},{"order":"ran","page":1,"of":4,"url":"/task/instruction-following/papers/ran/1","json":"/task/instruction-following/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":4,"url":"/task/instruction-following/papers/ran/2","json":"/task/instruction-following/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":4,"url":"/task/instruction-following/papers/ran/3","json":"/task/instruction-following/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":4,"url":"/task/instruction-following/papers/ran/4","json":"/task/instruction-following/papers/ran/4.json","rows":11}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"6216c207969f5b5e3f5881f9a33cf32095f43e280e46f38d430116c26750cf9a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}