{"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/large-language-model","name":"Large Language Model","slug":"large-language-model","description_markdown":null,"categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Methodology","url":"/area/methodology"},{"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":6097,"papers_with_code":2250,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":10,"subtasks":3,"parent_tasks":2},"benchmarks":[],"datasets":[{"url":"/dataset/ifeval","name":"IFEval","full_name":"Instruction Following Evaluation Datset","num_papers_in_archive":180},{"url":"/dataset/medconceptsqa","name":"MedConceptsQA","full_name":"","num_papers_in_archive":13},{"url":"/dataset/triviahg","name":"TriviaHG","full_name":"","num_papers_in_archive":3},{"url":"/dataset/human-simulacra","name":"Human Simulacra","full_name":"","num_papers_in_archive":2},{"url":"/dataset/diaforge-utc-r-0725","name":"diaforge-utc-r-0725","full_name":"DiaFORGE UTC: Unified Tool-Calling Conversations Dataset","num_papers_in_archive":1},{"url":"/dataset/glotsparse","name":"GlotSparse","full_name":"","num_papers_in_archive":1},{"url":"/dataset/hixstest","name":"HiXSTest","full_name":"Hindi XSTest","num_papers_in_archive":1},{"url":"/dataset/rpeval","name":"RPEval","full_name":"Role-Playing Evaluation Dataset","num_papers_in_archive":1},{"url":"/dataset/sgxstest","name":"SGXSTest","full_name":"Singapore XSTest","num_papers_in_archive":1},{"url":"/dataset/vmd","name":"VMD","full_name":"Virtual Moderation Dataset","num_papers_in_archive":1}],"subtasks":[{"url":"/task/ai-agent","name":"AI Agent"},{"url":"/task/knowledge-graphs","name":"Knowledge Graphs"},{"url":"/task/rag","name":"RAG"}],"parent_tasks":[{"url":"/task/inductive-knowledge-graph-completion","name":"Inductive knowledge graph completion"},{"url":"/task/knowledge-graph-completion","name":"Knowledge Graph Completion"}],"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":61,"rows_per_page":100,"shown":100,"of":6097,"of_with_code":2250,"tagged_in_all":6097,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":651,"every_run_a_failure_of_syntologys_instrument":150,"listed_with_a_run_with_no_instrument_failure":651,"listed_every_run_a_failure_of_syntologys_instrument":150,"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/judging-llm-as-a-judge-with-mt-bench-and-1","slug":"judging-llm-as-a-judge-with-mt-bench-and-1","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","date":"2023-06-09","arxiv_id":"2306.05685","repositories_listed":11,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1#ran","syntology_url":"https://syntology.ai/paper/2306.05685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05685"}},"official":{"repos":["lm-sys/fastchat"],"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/generative-agents-interactive-simulacra-of","slug":"generative-agents-interactive-simulacra-of","title":"Generative Agents: Interactive Simulacra of Human Behavior","date":"2023-04-07","arxiv_id":"2304.03442","repositories_listed":8,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generative-agents-interactive-simulacra-of#ran","syntology_url":"https://syntology.ai/paper/2304.03442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03442"}},"official":{"repos":["joonspk-research/generative_agents"],"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":["listed","official"]}}},{"url":"/paper/a-conversational-paradigm-for-program","slug":"a-conversational-paradigm-for-program","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","date":"2022-03-25","arxiv_id":"2203.13474","repositories_listed":8,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"10 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; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-conversational-paradigm-for-program#ran","syntology_url":"https://syntology.ai/paper/2203.13474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13474"}},"official":{"repos":["salesforce/CodeGen","salesforce/jaxformer"],"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":["listed","official"]}}},{"url":"/paper/hybridflow-a-flexible-and-efficient-rlhf","slug":"hybridflow-a-flexible-and-efficient-rlhf","title":"HybridFlow: A Flexible and Efficient RLHF Framework","date":"2024-09-28","arxiv_id":"2409.19256","repositories_listed":7,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/hybridflow-a-flexible-and-efficient-rlhf#ran","syntology_url":"https://syntology.ai/paper/2409.19256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19256"}},"official":null}},{"url":"/paper/2309-06180","slug":"2309-06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","date":"2023-09-12","arxiv_id":"2309.06180","repositories_listed":7,"syntology":{"n":36,"n_ran":28,"n_constructed":0,"n_ran_checked":12,"n_instrument":16,"n_unverified":8,"n_honours":5,"n_violates":1,"n_no_contract":6,"n_pointer_only":11,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 5 honoured, 1 violated, 6 with no contract checked; 16 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/2309-06180#ran","syntology_url":"https://syntology.ai/paper/2309.06180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06180"}},"official":{"repos":["vllm-project/vllm"],"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/an-example-of-evolutionary-computation-large","slug":"an-example-of-evolutionary-computation-large","title":"Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model","date":"2024-01-04","arxiv_id":"2401.02051","repositories_listed":6,"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/an-example-of-evolutionary-computation-large#ran","syntology_url":"https://syntology.ai/paper/2401.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02051"}},"official":{"repos":["feiliu36/eoh"],"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/video-llava-learning-united-visual-1","slug":"video-llava-learning-united-visual-1","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","date":"2023-11-16","arxiv_id":"2311.10122","repositories_listed":6,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-llava-learning-united-visual-1#ran","syntology_url":"https://syntology.ai/paper/2311.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10122"}},"official":{"repos":["PKU-YuanGroup/Video-LLaVA"],"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/deepspeed-ulysses-system-optimizations-for","slug":"deepspeed-ulysses-system-optimizations-for","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","date":"2023-09-25","arxiv_id":"2309.14509","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepspeed-ulysses-system-optimizations-for#ran","syntology_url":"https://syntology.ai/paper/2309.14509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14509"}},"official":null}},{"url":"/paper/minigpt-4-enhancing-vision-language","slug":"minigpt-4-enhancing-vision-language","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","date":"2023-04-20","arxiv_id":"2304.10592","repositories_listed":6,"syntology":null},{"url":"/paper/xiyan-sql-a-multi-generator-ensemble","slug":"xiyan-sql-a-multi-generator-ensemble","title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","date":"2024-11-13","arxiv_id":"2411.08599","repositories_listed":5,"syntology":null},{"url":"/paper/llm-as-os-llmao-agents-as-apps-envisioning","slug":"llm-as-os-llmao-agents-as-apps-envisioning","title":"LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem","date":"2023-12-06","arxiv_id":"2312.03815","repositories_listed":5,"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/llm-as-os-llmao-agents-as-apps-envisioning#ran","syntology_url":"https://syntology.ai/paper/2312.03815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03815"}},"official":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/baize-an-open-source-chat-model-with","slug":"baize-an-open-source-chat-model-with","title":"Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data","date":"2023-04-03","arxiv_id":"2304.01196","repositories_listed":5,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/baize-an-open-source-chat-model-with#ran","syntology_url":"https://syntology.ai/paper/2304.01196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01196"}},"official":{"repos":["project-baize/baize","project-baize/baize-chatbot"],"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/accelerating-large-language-model-decoding","slug":"accelerating-large-language-model-decoding","title":"Accelerating Large Language Model Decoding with Speculative Sampling","date":"2023-02-02","arxiv_id":"2302.01318","repositories_listed":5,"syntology":null},{"url":"/paper/muse-text-to-image-generation-via-masked","slug":"muse-text-to-image-generation-via-masked","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","date":"2023-01-02","arxiv_id":"2301.00704","repositories_listed":5,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":8,"n_instrument":11,"n_unverified":2,"n_honours":2,"n_violates":5,"n_no_contract":1,"n_pointer_only":11,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 5 violated, 1 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/muse-text-to-image-generation-via-masked#ran","syntology_url":"https://syntology.ai/paper/2301.00704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00704"}},"official":null}},{"url":"/paper/a-mem-agentic-memory-for-llm-agents","slug":"a-mem-agentic-memory-for-llm-agents","title":"A-MEM: Agentic Memory for LLM Agents","date":"2025-02-17","arxiv_id":"2502.12110","repositories_listed":4,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-mem-agentic-memory-for-llm-agents#ran","syntology_url":"https://syntology.ai/paper/2502.12110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12110"}},"official":{"repos":["agiresearch/a-mem","wujiangxu/agenticmemory"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-synthetic-data-creation-with","slug":"scaling-synthetic-data-creation-with","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","date":"2024-06-28","arxiv_id":"2406.20094","repositories_listed":4,"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":1,"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/scaling-synthetic-data-creation-with#ran","syntology_url":"https://syntology.ai/paper/2406.20094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20094"}},"official":{"repos":["tencent-ailab/persona-hub"],"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/ranking-manipulation-for-conversational","slug":"ranking-manipulation-for-conversational","title":"Ranking Manipulation for Conversational Search Engines","date":"2024-06-05","arxiv_id":"2406.03589","repositories_listed":4,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":20,"phrase":"12 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; 7 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/ranking-manipulation-for-conversational#ran","syntology_url":"https://syntology.ai/paper/2406.03589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03589"}},"official":{"repos":["spfrommer/ragdoll-data-pipeline","spfrommer/ranking_manipulation","spfrommer/ranking_manipulation_data_pipeline","spfrommer/cse-ranking-manipulation"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/qserve-w4a8kv4-quantization-and-system-co","slug":"qserve-w4a8kv4-quantization-and-system-co","title":"QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving","date":"2024-05-07","arxiv_id":"2405.04532","repositories_listed":4,"syntology":null},{"url":"/paper/tower-an-open-multilingual-large-language","slug":"tower-an-open-multilingual-large-language","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","date":"2024-02-27","arxiv_id":"2402.17733","repositories_listed":4,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"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) · 0 unverified","sample_list":"/paper/tower-an-open-multilingual-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.17733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17733"}},"official":{"repos":["deep-spin/tower-eval","epfllm/megatron-llm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/x-lora-mixture-of-low-rank-adapter-experts-a","slug":"x-lora-mixture-of-low-rank-adapter-experts-a","title":"X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design","date":"2024-02-11","arxiv_id":"2402.07148","repositories_listed":4,"syntology":null},{"url":"/paper/algorithm-evolution-using-large-language","slug":"algorithm-evolution-using-large-language","title":"Algorithm Evolution Using Large Language Model","date":"2023-11-26","arxiv_id":"2311.15249","repositories_listed":4,"syntology":null},{"url":"/paper/nlp-evaluation-in-trouble-on-the-need-to","slug":"nlp-evaluation-in-trouble-on-the-need-to","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","date":"2023-10-27","arxiv_id":"2310.18018","repositories_listed":4,"syntology":null},{"url":"/paper/llemma-an-open-language-model-for-mathematics","slug":"llemma-an-open-language-model-for-mathematics","title":"Llemma: An Open Language Model For Mathematics","date":"2023-10-16","arxiv_id":"2310.10631","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llemma-an-open-language-model-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}},"official":{"repos":["EleutherAI/math-lm","eleutherai/gpt-neox","wellecks/llmstep"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/how-is-chatgpt-s-behavior-changing-over-time","slug":"how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"6 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-is-chatgpt-s-behavior-changing-over-time#ran","syntology_url":"https://syntology.ai/paper/2307.09009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09009"}},"official":{"repos":["lchen001/llmdrift"],"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/hyenadna-long-range-genomic-sequence-modeling","slug":"hyenadna-long-range-genomic-sequence-modeling","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","date":"2023-06-27","arxiv_id":"2306.15794","repositories_listed":4,"syntology":{"n":28,"n_ran":17,"n_constructed":11,"n_ran_checked":13,"n_instrument":4,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":1,"phrase":"17 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/hyenadna-long-range-genomic-sequence-modeling#ran","syntology_url":"https://syntology.ai/paper/2306.15794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15794"}},"official":{"repos":["HazyResearch/hyena-dna"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mme-a-comprehensive-evaluation-benchmark-for","slug":"mme-a-comprehensive-evaluation-benchmark-for","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","date":"2023-06-23","arxiv_id":"2306.13394","repositories_listed":4,"syntology":null},{"url":"/paper/deeptextmark-deep-learning-based-text","slug":"deeptextmark-deep-learning-based-text","title":"DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated Text","date":"2023-05-09","arxiv_id":"2305.05773","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/deeptextmark-deep-learning-based-text#ran","syntology_url":"https://syntology.ai/paper/2305.05773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05773"}},"official":null}},{"url":"/paper/protoformer-embedding-prototypes-for-1","slug":"protoformer-embedding-prototypes-for-1","title":"Protoformer: Embedding Prototypes for Transformers","date":"2022-06-25","arxiv_id":"2206.12710","repositories_listed":4,"syntology":null},{"url":"/paper/fast-transformer-decoding-one-write-head-is","slug":"fast-transformer-decoding-one-write-head-is","title":"Fast Transformer Decoding: One Write-Head is All You Need","date":"2019-11-06","arxiv_id":"1911.02150","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/fast-transformer-decoding-one-write-head-is#ran","syntology_url":"https://syntology.ai/paper/1911.02150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02150"}},"official":null}},{"url":"/paper/moshi-a-speech-text-foundation-model-for-real","slug":"moshi-a-speech-text-foundation-model-for-real","title":"Moshi: a speech-text foundation model for real-time dialogue","date":"2024-09-17","arxiv_id":"2410.00037","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"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; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moshi-a-speech-text-foundation-model-for-real#ran","syntology_url":"https://syntology.ai/paper/2410.00037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00037"}},"official":{"repos":["kyutai-labs/moshi"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/task-level-distributionally-robust","slug":"task-level-distributionally-robust","title":"Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval","date":"2024-08-20","arxiv_id":"2408.10613","repositories_listed":3,"syntology":null},{"url":"/paper/mavis-mathematical-visual-instruction-tuning","slug":"mavis-mathematical-visual-instruction-tuning","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","date":"2024-07-11","arxiv_id":"2407.08739","repositories_listed":3,"syntology":null},{"url":"/paper/large-language-model-validity-via-enhanced","slug":"large-language-model-validity-via-enhanced","title":"Large language model validity via enhanced conformal prediction methods","date":"2024-06-14","arxiv_id":"2406.09714","repositories_listed":3,"syntology":{"n":32,"n_ran":23,"n_constructed":0,"n_ran_checked":18,"n_instrument":5,"n_unverified":9,"n_honours":3,"n_violates":2,"n_no_contract":13,"n_pointer_only":12,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 3 honoured, 2 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/large-language-model-validity-via-enhanced#ran","syntology_url":"https://syntology.ai/paper/2406.09714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09714"}},"official":{"repos":["jjcherian/conformal-safety"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/discovering-preference-optimization","slug":"discovering-preference-optimization","title":"Discovering Preference Optimization Algorithms with and for Large Language Models","date":"2024-06-12","arxiv_id":"2406.08414","repositories_listed":3,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"7 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/discovering-preference-optimization#ran","syntology_url":"https://syntology.ai/paper/2406.08414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08414"}},"official":{"repos":["luchris429/DiscoPOP","samholt/DiscoPOP","vanderschaarlab/discopop"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mixture-of-agents-enhances-large-language","slug":"mixture-of-agents-enhances-large-language","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","date":"2024-06-07","arxiv_id":"2406.04692","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mixture-of-agents-enhances-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.04692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04692"}},"official":null}},{"url":"/paper/4d-panoptic-scene-graph-generation-1","slug":"4d-panoptic-scene-graph-generation-1","title":"4D Panoptic Scene Graph Generation","date":"2024-05-16","arxiv_id":"2405.10305","repositories_listed":3,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":1,"n_honours":3,"n_violates":1,"n_no_contract":5,"n_pointer_only":10,"phrase":"13 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/4d-panoptic-scene-graph-generation-1#ran","syntology_url":"https://syntology.ai/paper/2405.10305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10305"}},"official":{"repos":["jingkang50/psg4d","Jingkang50/OpenPSG","jingkang50/openpvsg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rlhf-workflow-from-reward-modeling-to-online","slug":"rlhf-workflow-from-reward-modeling-to-online","title":"RLHF Workflow: From Reward Modeling to Online RLHF","date":"2024-05-13","arxiv_id":"2405.07863","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/rlhf-workflow-from-reward-modeling-to-online#ran","syntology_url":"https://syntology.ai/paper/2405.07863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07863"}},"official":{"repos":["RLHFlow/RLHF-Reward-Modeling","rlhflow/online-rlhf"],"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/analyzing-the-impact-of-data-selection-and","slug":"analyzing-the-impact-of-data-selection-and","title":"PoliTune: Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in Large Language Models","date":"2024-04-10","arxiv_id":"2404.08699","repositories_listed":3,"syntology":null},{"url":"/paper/visual-autoregressive-modeling-scalable-image","slug":"visual-autoregressive-modeling-scalable-image","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","date":"2024-04-03","arxiv_id":"2404.02905","repositories_listed":3,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/visual-autoregressive-modeling-scalable-image#ran","syntology_url":"https://syntology.ai/paper/2404.02905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02905"}},"official":{"repos":["FoundationVision/VAR"],"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/jamba-a-hybrid-transformer-mamba-language","slug":"jamba-a-hybrid-transformer-mamba-language","title":"Jamba: A Hybrid Transformer-Mamba Language Model","date":"2024-03-28","arxiv_id":"2403.19887","repositories_listed":3,"syntology":null},{"url":"/paper/guardt2i-defending-text-to-image-models-from","slug":"guardt2i-defending-text-to-image-models-from","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","date":"2024-03-03","arxiv_id":"2403.01446","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":2,"n_instrument":7,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":12,"phrase":"9 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; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/guardt2i-defending-text-to-image-models-from#ran","syntology_url":"https://syntology.ai/paper/2403.01446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01446"}},"official":{"repos":["cure-lab/guardt2i"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/retrieval-augmented-generation-for-ai","slug":"retrieval-augmented-generation-for-ai","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","date":"2024-02-29","arxiv_id":"2402.19473","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/spatial-temporal-large-language-model-for","slug":"spatial-temporal-large-language-model-for","title":"Spatial-Temporal Large Language Model for Traffic Prediction","date":"2024-01-18","arxiv_id":"2401.10134","repositories_listed":3,"syntology":null},{"url":"/paper/know-your-needs-better-towards-structured","slug":"know-your-needs-better-towards-structured","title":"Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs","date":"2024-01-09","arxiv_id":"2401.04319","repositories_listed":3,"syntology":null},{"url":"/paper/g-llava-solving-geometric-problem-with-multi","slug":"g-llava-solving-geometric-problem-with-multi","title":"G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model","date":"2023-12-18","arxiv_id":"2312.11370","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 2 unverified","sample_list":"/paper/g-llava-solving-geometric-problem-with-multi#ran","syntology_url":"https://syntology.ai/paper/2312.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11370"}},"official":{"repos":["pipilurj/g-llava"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/gibbs-sampling-from-human-feedback-a-provable","slug":"gibbs-sampling-from-human-feedback-a-provable","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","date":"2023-12-18","arxiv_id":"2312.11456","repositories_listed":3,"syntology":null},{"url":"/paper/a-survey-of-graph-meets-large-language-model","slug":"a-survey-of-graph-meets-large-language-model","title":"A Survey of Graph Meets Large Language Model: Progress and Future Directions","date":"2023-11-21","arxiv_id":"2311.12399","repositories_listed":3,"syntology":null},{"url":"/paper/prometheus-inducing-fine-grained-evaluation","slug":"prometheus-inducing-fine-grained-evaluation","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","date":"2023-10-12","arxiv_id":"2310.08491","repositories_listed":3,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/prometheus-inducing-fine-grained-evaluation#ran","syntology_url":"https://syntology.ai/paper/2310.08491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08491"}},"official":{"repos":["kaistAI/Prometheus"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/structchart-perception-structuring-reasoning","slug":"structchart-perception-structuring-reasoning","title":"StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding","date":"2023-09-20","arxiv_id":"2309.11268","repositories_listed":3,"syntology":null},{"url":"/paper/music-understanding-llama-advancing-text-to","slug":"music-understanding-llama-advancing-text-to","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","date":"2023-08-22","arxiv_id":"2308.11276","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/music-understanding-llama-advancing-text-to#ran","syntology_url":"https://syntology.ai/paper/2308.11276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11276"}},"official":{"repos":["crypto-code/mu-llama"],"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/beam-retrieval-general-end-to-end-retrieval","slug":"beam-retrieval-general-end-to-end-retrieval","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","date":"2023-08-17","arxiv_id":"2308.08973","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/beam-retrieval-general-end-to-end-retrieval#ran","syntology_url":"https://syntology.ai/paper/2308.08973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08973"}},"official":{"repos":["Alab-NII/2wikimultihop","canghongjian/beam_retriever"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/studying-large-language-model-generalization","slug":"studying-large-language-model-generalization","title":"Studying Large Language Model Generalization with Influence Functions","date":"2023-08-07","arxiv_id":"2308.03296","repositories_listed":3,"syntology":null},{"url":"/paper/think-on-graph-deep-and-responsible-reasoning","slug":"think-on-graph-deep-and-responsible-reasoning","title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph","date":"2023-07-15","arxiv_id":"2307.07697","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":3,"n_no_contract":6,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 3 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/think-on-graph-deep-and-responsible-reasoning#ran","syntology_url":"https://syntology.ai/paper/2307.07697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07697"}},"official":{"repos":["gasolsun36/tog","idea-finai/tog"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["community","official"]}}},{"url":"/paper/gpt4roi-instruction-tuning-large-language","slug":"gpt4roi-instruction-tuning-large-language","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","date":"2023-07-07","arxiv_id":"2307.03601","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gpt4roi-instruction-tuning-large-language#ran","syntology_url":"https://syntology.ai/paper/2307.03601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03601"}},"official":{"repos":["jshilong/gpt4roi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-prompting-assists-large-language","slug":"hierarchical-prompting-assists-large-language","title":"Hierarchical Prompting Assists Large Language Model on Web Navigation","date":"2023-05-23","arxiv_id":"2305.14257","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hierarchical-prompting-assists-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14257"}},"official":{"repos":["robert1003/ash-prompting"],"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/specinfer-accelerating-generative-llm-serving","slug":"specinfer-accelerating-generative-llm-serving","title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification","date":"2023-05-16","arxiv_id":"2305.09781","repositories_listed":3,"syntology":null},{"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/wavcaps-a-chatgpt-assisted-weakly-labelled","slug":"wavcaps-a-chatgpt-assisted-weakly-labelled","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","date":"2023-03-30","arxiv_id":"2303.17395","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled#ran","syntology_url":"https://syntology.ai/paper/2303.17395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17395"}},"official":{"repos":["xinhaomei/wavcaps"],"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/cost-effective-hyperparameter-optimization","slug":"cost-effective-hyperparameter-optimization","title":"Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference","date":"2023-03-08","arxiv_id":"2303.04673","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cost-effective-hyperparameter-optimization#ran","syntology_url":"https://syntology.ai/paper/2303.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04673"}},"official":{"repos":["microsoft/FLAML"],"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/openicl-an-open-source-framework-for-in","slug":"openicl-an-open-source-framework-for-in","title":"OpenICL: An Open-Source Framework for In-context Learning","date":"2023-03-06","arxiv_id":"2303.02913","repositories_listed":3,"syntology":null},{"url":"/paper/raise-a-child-in-large-language-model-towards","slug":"raise-a-child-in-large-language-model-towards","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","date":"2021-09-13","arxiv_id":"2109.05687","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/raise-a-child-in-large-language-model-towards#ran","syntology_url":"https://syntology.ai/paper/2109.05687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05687"}},"official":{"repos":["alibaba/AliceMind","pkunlp-icler/childtuning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dataset-distillation-via-vision-language","slug":"dataset-distillation-via-vision-language","title":"Dataset Distillation via Vision-Language Category Prototype","date":"2025-06-30","arxiv_id":"2506.23580","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/dataset-distillation-via-vision-language#ran","syntology_url":"https://syntology.ai/paper/2506.23580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.23580"}},"official":{"repos":["Guang000/Awesome-Dataset-Distillation","zou-yawen/dataset-distillation-via-vision-language-category-prototype"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/actalign-zero-shot-fine-grained-video","slug":"actalign-zero-shot-fine-grained-video","title":"ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment","date":"2025-06-28","arxiv_id":"2506.22967","repositories_listed":2,"syntology":null},{"url":"/paper/stream-omni-simultaneous-multimodal","slug":"stream-omni-simultaneous-multimodal","title":"Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model","date":"2025-06-16","arxiv_id":"2506.13642","repositories_listed":2,"syntology":null},{"url":"/paper/2506-08762","slug":"2506-08762","title":"EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements","date":"2025-06-10","arxiv_id":"2506.08762","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2506-08762#ran","syntology_url":"https://syntology.ai/paper/2506.08762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08762"}},"official":{"repos":["sakanaai/edinet-bench","sakanaai/edinet2dataset"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llamea-bo-a-large-language-model-evolutionary","slug":"llamea-bo-a-large-language-model-evolutionary","title":"LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms","date":"2025-05-27","arxiv_id":"2505.21034","repositories_listed":2,"syntology":null},{"url":"/paper/a-survey-of-llm-times-data","slug":"a-survey-of-llm-times-data","title":"A Survey of LLM $\\times$ DATA","date":"2025-05-24","arxiv_id":"2505.18458","repositories_listed":2,"syntology":null},{"url":"/paper/cosyvoice-3-towards-in-the-wild-speech","slug":"cosyvoice-3-towards-in-the-wild-speech","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","date":"2025-05-23","arxiv_id":"2505.17589","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":1,"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/cosyvoice-3-towards-in-the-wild-speech#ran","syntology_url":"https://syntology.ai/paper/2505.17589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17589"}},"official":{"repos":["funaudiollm/cosyvoice"],"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/unitts-an-end-to-end-tts-system-without","slug":"unitts-an-end-to-end-tts-system-without","title":"UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information","date":"2025-05-23","arxiv_id":"2505.17426","repositories_listed":2,"syntology":null},{"url":"/paper/wirelessagent-large-language-model-agents-for-1","slug":"wirelessagent-large-language-model-agents-for-1","title":"WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks","date":"2025-05-02","arxiv_id":"2505.01074","repositories_listed":2,"syntology":null},{"url":"/paper/evaluation-report-on-mcp-servers","slug":"evaluation-report-on-mcp-servers","title":"Evaluation Report on MCP Servers","date":"2025-04-15","arxiv_id":"2504.11094","repositories_listed":2,"syntology":null},{"url":"/paper/kimina-prover-preview-towards-large-formal","slug":"kimina-prover-preview-towards-large-formal","title":"Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning","date":"2025-04-15","arxiv_id":"2504.11354","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":2,"n_no_contract":0,"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, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kimina-prover-preview-towards-large-formal#ran","syntology_url":"https://syntology.ai/paper/2504.11354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11354"}},"official":{"repos":["moonshotai/kimina-prover-preview"],"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/omni-dish-photorealistic-and-faithful-image","slug":"omni-dish-photorealistic-and-faithful-image","title":"Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes","date":"2025-04-14","arxiv_id":"2504.09948","repositories_listed":2,"syntology":null},{"url":"/paper/representation-bending-for-large-language","slug":"representation-bending-for-large-language","title":"Representation Bending for Large Language Model Safety","date":"2025-04-02","arxiv_id":"2504.01550","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/representation-bending-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2504.01550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01550"}},"official":{"repos":["aim-intelligence/repbend"],"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/whisper-lm-improving-asr-models-with-language","slug":"whisper-lm-improving-asr-models-with-language","title":"Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages","date":"2025-03-30","arxiv_id":"2503.23542","repositories_listed":2,"syntology":null},{"url":"/paper/relevance-isn-t-all-you-need-scaling-rag","slug":"relevance-isn-t-all-you-need-scaling-rag","title":"Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking","date":"2025-03-14","arxiv_id":"2504.07104","repositories_listed":2,"syntology":null},{"url":"/paper/reproducing-nevir-negation-in-neural","slug":"reproducing-nevir-negation-in-neural","title":"Reproducing NevIR: Negation in Neural Information Retrieval","date":"2025-02-19","arxiv_id":"2502.13506","repositories_listed":2,"syntology":null},{"url":"/paper/llms-can-easily-learn-to-reason-from","slug":"llms-can-easily-learn-to-reason-from","title":"LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!","date":"2025-02-11","arxiv_id":"2502.07374","repositories_listed":2,"syntology":null},{"url":"/paper/autoagent-a-fully-automated-and-zero-code","slug":"autoagent-a-fully-automated-and-zero-code","title":"AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents","date":"2025-02-09","arxiv_id":"2502.05957","repositories_listed":2,"syntology":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/lavcap-llm-based-audio-visual-captioning","slug":"lavcap-llm-based-audio-visual-captioning","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","date":"2025-01-16","arxiv_id":"2501.09291","repositories_listed":2,"syntology":null},{"url":"/paper/latent-reward-llm-empowered-credit-assignment","slug":"latent-reward-llm-empowered-credit-assignment","title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning","date":"2024-12-15","arxiv_id":"2412.11120","repositories_listed":2,"syntology":null},{"url":"/paper/pushing-the-limits-of-large-language-model","slug":"pushing-the-limits-of-large-language-model","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","date":"2024-11-26","arxiv_id":"2411.17525","repositories_listed":2,"syntology":{"n":36,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":15,"n_honours":0,"n_violates":1,"n_no_contract":19,"n_pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 1 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/pushing-the-limits-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.17525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17525"}},"official":null}},{"url":"/paper/learn-from-downstream-and-be-yourself-in","slug":"learn-from-downstream-and-be-yourself-in","title":"Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning","date":"2024-11-17","arxiv_id":"2411.10928","repositories_listed":2,"syntology":null},{"url":"/paper/llm-neo-parameter-efficient-knowledge","slug":"llm-neo-parameter-efficient-knowledge","title":"LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models","date":"2024-11-11","arxiv_id":"2411.06839","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-neo-parameter-efficient-knowledge#ran","syntology_url":"https://syntology.ai/paper/2411.06839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06839"}},"official":null}},{"url":"/paper/plan-on-graph-self-correcting-adaptive","slug":"plan-on-graph-self-correcting-adaptive","title":"Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs","date":"2024-10-31","arxiv_id":"2410.23875","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"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) · 5 unverified","sample_list":"/paper/plan-on-graph-self-correcting-adaptive#ran","syntology_url":"https://syntology.ai/paper/2410.23875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23875"}},"official":{"repos":["liyichen-cly/pog"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/swe-search-enhancing-software-agents-with","slug":"swe-search-enhancing-software-agents-with","title":"SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement","date":"2024-10-26","arxiv_id":"2410.20285","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/swe-search-enhancing-software-agents-with#ran","syntology_url":"https://syntology.ai/paper/2410.20285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20285"}},"official":{"repos":["aorwall/moatless-tools","aorwall/moatless-tree-search"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/graphteam-facilitating-large-language-model","slug":"graphteam-facilitating-large-language-model","title":"GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration","date":"2024-10-23","arxiv_id":"2410.18032","repositories_listed":2,"syntology":null},{"url":"/paper/pldr-llm-large-language-model-from-power-law","slug":"pldr-llm-large-language-model-from-power-law","title":"PLDR-LLM: Large Language Model from Power Law Decoder Representations","date":"2024-10-22","arxiv_id":"2410.16703","repositories_listed":2,"syntology":null},{"url":"/paper/baichuan-omni-technical-report","slug":"baichuan-omni-technical-report","title":"Baichuan-Omni Technical Report","date":"2024-10-11","arxiv_id":"2410.08565","repositories_listed":2,"syntology":null},{"url":"/paper/simplicity-prevails-rethinking-negative","slug":"simplicity-prevails-rethinking-negative","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","date":"2024-10-09","arxiv_id":"2410.07163","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/simplicity-prevails-rethinking-negative#ran","syntology_url":"https://syntology.ai/paper/2410.07163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07163"}},"official":{"repos":["OPTML-Group/Unlearn-Simple"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/improver-agent-based-automated-proof","slug":"improver-agent-based-automated-proof","title":"ImProver: Agent-Based Automated Proof Optimization","date":"2024-10-07","arxiv_id":"2410.04753","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/improver-agent-based-automated-proof#ran","syntology_url":"https://syntology.ai/paper/2410.04753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04753"}},"official":{"repos":["riyazahuja/ImProver"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/colacare-enhancing-electronic-health-record","slug":"colacare-enhancing-electronic-health-record","title":"ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration","date":"2024-10-03","arxiv_id":"2410.02551","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-model-empowered-embedding","slug":"large-language-model-empowered-embedding","title":"LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation","date":"2024-09-30","arxiv_id":"2409.19925","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-model-empowered-embedding#ran","syntology_url":"https://syntology.ai/paper/2409.19925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19925"}},"official":{"repos":["applied-machine-learning-lab/llmemb","liuqidong07/LLMEmb"],"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/data-prep-kit-getting-your-data-ready-for-llm","slug":"data-prep-kit-getting-your-data-ready-for-llm","title":"Data-Prep-Kit: getting your data ready for LLM application development","date":"2024-09-26","arxiv_id":"2409.18164","repositories_listed":2,"syntology":null},{"url":"/paper/recoverable-compression-a-multimodal-vision","slug":"recoverable-compression-a-multimodal-vision","title":"Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information","date":"2024-09-02","arxiv_id":"2409.01179","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/recoverable-compression-a-multimodal-vision#ran","syntology_url":"https://syntology.ai/paper/2409.01179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01179"}},"official":{"repos":["banjiuyufen/recoverablecompression","banjiuyufen/Recoverable-Compression"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/pedestrian-attribute-recognition-a-new","slug":"pedestrian-attribute-recognition-a-new","title":"Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework","date":"2024-08-19","arxiv_id":"2408.09720","repositories_listed":2,"syntology":null},{"url":"/paper/utilizing-large-language-models-to-optimize","slug":"utilizing-large-language-models-to-optimize","title":"PhishLang: A Real-Time, Fully Client-Side Phishing Detection Framework Using MobileBERT","date":"2024-08-11","arxiv_id":"2408.05667","repositories_listed":2,"syntology":null}],"syntology_records":54,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":801,"papers_where_code_ran_first_page":"/task/large-language-model/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":61,"url":"/task/large-language-model/papers/2","json":"/task/large-language-model/papers/2.json","rows":100},{"order":"archive","page":3,"of":61,"url":"/task/large-language-model/papers/3","json":"/task/large-language-model/papers/3.json","rows":100},{"order":"archive","page":4,"of":61,"url":"/task/large-language-model/papers/4","json":"/task/large-language-model/papers/4.json","rows":100},{"order":"archive","page":5,"of":61,"url":"/task/large-language-model/papers/5","json":"/task/large-language-model/papers/5.json","rows":100},{"order":"archive","page":6,"of":61,"url":"/task/large-language-model/papers/6","json":"/task/large-language-model/papers/6.json","rows":100},{"order":"archive","page":7,"of":61,"url":"/task/large-language-model/papers/7","json":"/task/large-language-model/papers/7.json","rows":100},{"order":"archive","page":8,"of":61,"url":"/task/large-language-model/papers/8","json":"/task/large-language-model/papers/8.json","rows":100},{"order":"archive","page":9,"of":61,"url":"/task/large-language-model/papers/9","json":"/task/large-language-model/papers/9.json","rows":100},{"order":"archive","page":10,"of":61,"url":"/task/large-language-model/papers/10","json":"/task/large-language-model/papers/10.json","rows":100},{"order":"archive","page":11,"of":61,"url":"/task/large-language-model/papers/11","json":"/task/large-language-model/papers/11.json","rows":100},{"order":"archive","page":12,"of":61,"url":"/task/large-language-model/papers/12","json":"/task/large-language-model/papers/12.json","rows":100},{"order":"archive","page":13,"of":61,"url":"/task/large-language-model/papers/13","json":"/task/large-language-model/papers/13.json","rows":100},{"order":"archive","page":14,"of":61,"url":"/task/large-language-model/papers/14","json":"/task/large-language-model/papers/14.json","rows":100},{"order":"archive","page":15,"of":61,"url":"/task/large-language-model/papers/15","json":"/task/large-language-model/papers/15.json","rows":100},{"order":"archive","page":16,"of":61,"url":"/task/large-language-model/papers/16","json":"/task/large-language-model/papers/16.json","rows":100},{"order":"archive","page":17,"of":61,"url":"/task/large-language-model/papers/17","json":"/task/large-language-model/papers/17.json","rows":100},{"order":"archive","page":18,"of":61,"url":"/task/large-language-model/papers/18","json":"/task/large-language-model/papers/18.json","rows":100},{"order":"archive","page":19,"of":61,"url":"/task/large-language-model/papers/19","json":"/task/large-language-model/papers/19.json","rows":100},{"order":"archive","page":20,"of":61,"url":"/task/large-language-model/papers/20","json":"/task/large-language-model/papers/20.json","rows":100},{"order":"archive","page":21,"of":61,"url":"/task/large-language-model/papers/21","json":"/task/large-language-model/papers/21.json","rows":100},{"order":"archive","page":22,"of":61,"url":"/task/large-language-model/papers/22","json":"/task/large-language-model/papers/22.json","rows":100},{"order":"archive","page":23,"of":61,"url":"/task/large-language-model/papers/23","json":"/task/large-language-model/papers/23.json","rows":100},{"order":"archive","page":24,"of":61,"url":"/task/large-language-model/papers/24","json":"/task/large-language-model/papers/24.json","rows":100},{"order":"archive","page":25,"of":61,"url":"/task/large-language-model/papers/25","json":"/task/large-language-model/papers/25.json","rows":100},{"order":"archive","page":26,"of":61,"url":"/task/large-language-model/papers/26","json":"/task/large-language-model/papers/26.json","rows":100},{"order":"archive","page":27,"of":61,"url":"/task/large-language-model/papers/27","json":"/task/large-language-model/papers/27.json","rows":100},{"order":"archive","page":28,"of":61,"url":"/task/large-language-model/papers/28","json":"/task/large-language-model/papers/28.json","rows":100},{"order":"archive","page":29,"of":61,"url":"/task/large-language-model/papers/29","json":"/task/large-language-model/papers/29.json","rows":100},{"order":"archive","page":30,"of":61,"url":"/task/large-language-model/papers/30","json":"/task/large-language-model/papers/30.json","rows":100},{"order":"archive","page":31,"of":61,"url":"/task/large-language-model/papers/31","json":"/task/large-language-model/papers/31.json","rows":100},{"order":"archive","page":32,"of":61,"url":"/task/large-language-model/papers/32","json":"/task/large-language-model/papers/32.json","rows":100},{"order":"archive","page":33,"of":61,"url":"/task/large-language-model/papers/33","json":"/task/large-language-model/papers/33.json","rows":100},{"order":"archive","page":34,"of":61,"url":"/task/large-language-model/papers/34","json":"/task/large-language-model/papers/34.json","rows":100},{"order":"archive","page":35,"of":61,"url":"/task/large-language-model/papers/35","json":"/task/large-language-model/papers/35.json","rows":100},{"order":"archive","page":36,"of":61,"url":"/task/large-language-model/papers/36","json":"/task/large-language-model/papers/36.json","rows":100},{"order":"archive","page":37,"of":61,"url":"/task/large-language-model/papers/37","json":"/task/large-language-model/papers/37.json","rows":100},{"order":"archive","page":38,"of":61,"url":"/task/large-language-model/papers/38","json":"/task/large-language-model/papers/38.json","rows":100},{"order":"archive","page":39,"of":61,"url":"/task/large-language-model/papers/39","json":"/task/large-language-model/papers/39.json","rows":100},{"order":"archive","page":40,"of":61,"url":"/task/large-language-model/papers/40","json":"/task/large-language-model/papers/40.json","rows":100},{"order":"archive","page":41,"of":61,"url":"/task/large-language-model/papers/41","json":"/task/large-language-model/papers/41.json","rows":100},{"order":"archive","page":42,"of":61,"url":"/task/large-language-model/papers/42","json":"/task/large-language-model/papers/42.json","rows":100},{"order":"archive","page":43,"of":61,"url":"/task/large-language-model/papers/43","json":"/task/large-language-model/papers/43.json","rows":100},{"order":"archive","page":44,"of":61,"url":"/task/large-language-model/papers/44","json":"/task/large-language-model/papers/44.json","rows":100},{"order":"archive","page":45,"of":61,"url":"/task/large-language-model/papers/45","json":"/task/large-language-model/papers/45.json","rows":100},{"order":"archive","page":46,"of":61,"url":"/task/large-language-model/papers/46","json":"/task/large-language-model/papers/46.json","rows":100},{"order":"archive","page":47,"of":61,"url":"/task/large-language-model/papers/47","json":"/task/large-language-model/papers/47.json","rows":100},{"order":"archive","page":48,"of":61,"url":"/task/large-language-model/papers/48","json":"/task/large-language-model/papers/48.json","rows":100},{"order":"archive","page":49,"of":61,"url":"/task/large-language-model/papers/49","json":"/task/large-language-model/papers/49.json","rows":100},{"order":"archive","page":50,"of":61,"url":"/task/large-language-model/papers/50","json":"/task/large-language-model/papers/50.json","rows":100},{"order":"archive","page":51,"of":61,"url":"/task/large-language-model/papers/51","json":"/task/large-language-model/papers/51.json","rows":100},{"order":"archive","page":52,"of":61,"url":"/task/large-language-model/papers/52","json":"/task/large-language-model/papers/52.json","rows":100},{"order":"archive","page":53,"of":61,"url":"/task/large-language-model/papers/53","json":"/task/large-language-model/papers/53.json","rows":100},{"order":"archive","page":54,"of":61,"url":"/task/large-language-model/papers/54","json":"/task/large-language-model/papers/54.json","rows":100},{"order":"archive","page":55,"of":61,"url":"/task/large-language-model/papers/55","json":"/task/large-language-model/papers/55.json","rows":100},{"order":"archive","page":56,"of":61,"url":"/task/large-language-model/papers/56","json":"/task/large-language-model/papers/56.json","rows":100},{"order":"archive","page":57,"of":61,"url":"/task/large-language-model/papers/57","json":"/task/large-language-model/papers/57.json","rows":100},{"order":"archive","page":58,"of":61,"url":"/task/large-language-model/papers/58","json":"/task/large-language-model/papers/58.json","rows":100},{"order":"archive","page":59,"of":61,"url":"/task/large-language-model/papers/59","json":"/task/large-language-model/papers/59.json","rows":100},{"order":"archive","page":60,"of":61,"url":"/task/large-language-model/papers/60","json":"/task/large-language-model/papers/60.json","rows":100},{"order":"archive","page":61,"of":61,"url":"/task/large-language-model/papers/61","json":"/task/large-language-model/papers/61.json","rows":97},{"order":"ran","page":1,"of":9,"url":"/task/large-language-model/papers/ran/1","json":"/task/large-language-model/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":9,"url":"/task/large-language-model/papers/ran/2","json":"/task/large-language-model/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":9,"url":"/task/large-language-model/papers/ran/3","json":"/task/large-language-model/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":9,"url":"/task/large-language-model/papers/ran/4","json":"/task/large-language-model/papers/ran/4.json","rows":100},{"order":"ran","page":5,"of":9,"url":"/task/large-language-model/papers/ran/5","json":"/task/large-language-model/papers/ran/5.json","rows":100},{"order":"ran","page":6,"of":9,"url":"/task/large-language-model/papers/ran/6","json":"/task/large-language-model/papers/ran/6.json","rows":100},{"order":"ran","page":7,"of":9,"url":"/task/large-language-model/papers/ran/7","json":"/task/large-language-model/papers/ran/7.json","rows":100},{"order":"ran","page":8,"of":9,"url":"/task/large-language-model/papers/ran/8","json":"/task/large-language-model/papers/ran/8.json","rows":100},{"order":"ran","page":9,"of":9,"url":"/task/large-language-model/papers/ran/9","json":"/task/large-language-model/papers/ran/9.json","rows":1}],"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":"25f345a7229e776b2e67d0695bc008760bb22862dadcab37277672049beb060f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}