{"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/long-context-understanding","name":"Long-Context Understanding","slug":"long-context-understanding","description_markdown":null,"categories":[{"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":81,"papers_with_code":54,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/long-context-understanding-on-mmneedle","slug":"long-context-understanding-on-mmneedle","dataset":"MMNeedle","dataset_url":"/dataset/mmneedle","rows_in_archive":12,"metrics":["1 Image, 4*4 Stitching, Exact Accuracy","1 Image, 8*8 Stitching, Exact Accuracy","1 Image, 2*2 Stitching, Exact Accuracy","10 Images, 1*1 Stitching, Exact Accuracy","10 Images, 2*2 Stitching, Exact Accuracy","10 Images, 4*4 Stitching, Exact Accuracy","10 Images, 8*8 Stitching, Exact Accuracy"],"first_row_in_archive_order":{"model":"GPT-4o","paper_title":"GPT-4 Technical Report","paper_url":"/paper/gpt-4-technical-report-1","paper_date":"2023-03-15","arxiv_id":"2303.08774","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/long-context-understanding-on-ada-leval","slug":"long-context-understanding-on-ada-leval","dataset":"Ada-LEval (BestAnswer)","dataset_url":null,"rows_in_archive":10,"metrics":["1k","2k","4k","6k","8k","12k","16k","32k","64k","128k"],"first_row_in_archive_order":{"model":"GPT-4-Turbo-1106","paper_title":"GPT-4 Technical Report","paper_url":"/paper/gpt-4-technical-report-1","paper_date":"2023-03-15","arxiv_id":"2303.08774","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/long-context-understanding-on-ada-leval-tsort","slug":"long-context-understanding-on-ada-leval-tsort","dataset":"Ada-LEval (TSort)","dataset_url":null,"rows_in_archive":10,"metrics":["2k","4k","8k","16k","32k","64k","128k"],"first_row_in_archive_order":{"model":"GPT-4-Turbo-1106","paper_title":"GPT-4 Technical Report","paper_url":"/paper/gpt-4-technical-report-1","paper_date":"2023-03-15","arxiv_id":"2303.08774","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/long-context-understanding-on-l-eval","slug":"long-context-understanding-on-l-eval","dataset":"L-Eval","dataset_url":"/dataset/l-eval","rows_in_archive":4,"metrics":["Average Score"],"first_row_in_archive_order":{"model":"GALI(Llama3-8b-ins-4k-to-16k)","paper_title":"A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)","paper_url":"/paper/a-training-free-length-extrapolation-approach","paper_date":"2025-02-04","arxiv_id":"2502.02659","code_links":[{"title":"academycityl/gali","url":"https://github.com/academycityl/gali"}],"syntology":null}},{"leaderboard":"/sota/long-context-understanding-on-longbench","slug":"long-context-understanding-on-longbench","dataset":"LongBench","dataset_url":"/dataset/longbench","rows_in_archive":3,"metrics":["Average Score"],"first_row_in_archive_order":{"model":"GALI(Llama3-8b-ins-4k-to-16k)","paper_title":"A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)","paper_url":"/paper/a-training-free-length-extrapolation-approach","paper_date":"2025-02-04","arxiv_id":"2502.02659","code_links":[{"title":"academycityl/gali","url":"https://github.com/academycityl/gali"}],"syntology":null}}],"datasets":[{"url":"/dataset/l-eval","name":"L-Eval","full_name":"","num_papers_in_archive":43},{"url":"/dataset/mmneedle","name":"MMNeedle","full_name":"Multimodal Needle in a Haystack","num_papers_in_archive":12},{"url":"/dataset/longbench","name":"LongBench","full_name":"","num_papers_in_archive":8},{"url":"/dataset/nolima","name":"NoLiMa","full_name":"NoLiMa: Long-Context Evaluation Beyond Literal Matching","num_papers_in_archive":1}],"subtasks":[],"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":1,"rows_per_page":100,"shown":81,"of":81,"of_with_code":54,"tagged_in_all":81,"counts":{"archive_papers_tagged":81,"with_a_code_link":54,"where_syntology_ran_a_sample":28,"not_listed_spam_title":0,"listed":81,"listed_where_code_ran":28,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":21,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"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/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","repositories_listed":9,"syntology":{"n":21,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/glm-130b-an-open-bilingual-pre-trained-model#ran","syntology_url":"https://syntology.ai/paper/2210.02414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02414"}},"official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ruler-what-s-the-real-context-size-of-your","slug":"ruler-what-s-the-real-context-size-of-your","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","date":"2024-04-09","arxiv_id":"2404.06654","repositories_listed":6,"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":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) · 0 unverified","sample_list":"/paper/ruler-what-s-the-real-context-size-of-your#ran","syntology_url":"https://syntology.ai/paper/2404.06654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06654"}},"official":{"repos":["hsiehjackson/ruler"],"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/gated-delta-networks-improving-mamba2-with","slug":"gated-delta-networks-improving-mamba2-with","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","date":"2024-12-09","arxiv_id":"2412.06464","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gated-delta-networks-improving-mamba2-with#ran","syntology_url":"https://syntology.ai/paper/2412.06464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06464"}},"official":{"repos":["NVlabs/GatedDeltaNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cogvlm-visual-expert-for-pretrained-language","slug":"cogvlm-visual-expert-for-pretrained-language","title":"CogVLM: Visual Expert for Pretrained Language Models","date":"2023-11-06","arxiv_id":"2311.03079","repositories_listed":4,"syntology":null},{"url":"/paper/instructblip-towards-general-purpose-vision","slug":"instructblip-towards-general-purpose-vision","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","date":"2023-05-11","arxiv_id":"2305.06500","repositories_listed":4,"syntology":null},{"url":"/paper/fables-evaluating-faithfulness-and-content","slug":"fables-evaluating-faithfulness-and-content","title":"FABLES: Evaluating faithfulness and content selection in book-length summarization","date":"2024-04-01","arxiv_id":"2404.01261","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/fables-evaluating-faithfulness-and-content#ran","syntology_url":"https://syntology.ai/paper/2404.01261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01261"}},"official":{"repos":["mungg/fables"],"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/internlm2-technical-report","slug":"internlm2-technical-report","title":"InternLM2 Technical Report","date":"2024-03-26","arxiv_id":"2403.17297","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/internlm2-technical-report#ran","syntology_url":"https://syntology.ai/paper/2403.17297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17297"}},"official":null}},{"url":"/paper/longbench-a-bilingual-multitask-benchmark-for","slug":"longbench-a-bilingual-multitask-benchmark-for","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","date":"2023-08-28","arxiv_id":"2308.14508","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/longbench-a-bilingual-multitask-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2308.14508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14508"}},"official":{"repos":["thudm/longbench"],"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/l-citeeval-do-long-context-models-truly","slug":"l-citeeval-do-long-context-models-truly","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","date":"2024-10-03","arxiv_id":"2410.02115","repositories_listed":2,"syntology":null},{"url":"/paper/long-context-llms-struggle-with-long-in","slug":"long-context-llms-struggle-with-long-in","title":"Long-context LLMs Struggle with Long In-context Learning","date":"2024-04-02","arxiv_id":"2404.02060","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"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, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-context-llms-struggle-with-long-in#ran","syntology_url":"https://syntology.ai/paper/2404.02060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02060"}},"official":{"repos":["tiger-ai-lab/longiclbench"],"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/mplug-owl2-revolutionizing-multi-modal-large","slug":"mplug-owl2-revolutionizing-multi-modal-large","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","date":"2023-11-07","arxiv_id":"2311.04257","repositories_listed":2,"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":3,"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/mplug-owl2-revolutionizing-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2311.04257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04257"}},"official":{"repos":["x-plug/mplug-owl"],"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":["unlocated"]}}},{"url":"/paper/s3eval-a-synthetic-scalable-systematic","slug":"s3eval-a-synthetic-scalable-systematic","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","date":"2023-10-23","arxiv_id":"2310.15147","repositories_listed":2,"syntology":{"n":26,"n_ran":21,"n_constructed":0,"n_ran_checked":21,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":26,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/s3eval-a-synthetic-scalable-systematic#ran","syntology_url":"https://syntology.ai/paper/2310.15147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15147"}},"official":{"repos":["lfy79001/s3eval","lfy79001/sqleval"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":21,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/ref-long-benchmarking-the-long-context","slug":"ref-long-benchmarking-the-long-context","title":"Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models","date":"2025-07-13","arxiv_id":"2507.09506","repositories_listed":1,"syntology":null},{"url":"/paper/cache-me-if-you-can-how-many-kvs-do-you-need","slug":"cache-me-if-you-can-how-many-kvs-do-you-need","title":"Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?","date":"2025-06-20","arxiv_id":"2506.17121","repositories_listed":1,"syntology":null},{"url":"/paper/dam-dynamic-attention-mask-for-long-context","slug":"dam-dynamic-attention-mask-for-long-context","title":"DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration","date":"2025-06-06","arxiv_id":"2506.11104","repositories_listed":1,"syntology":null},{"url":"/paper/mesanet-sequence-modeling-by-locally-optimal","slug":"mesanet-sequence-modeling-by-locally-optimal","title":"MesaNet: Sequence Modeling by Locally Optimal Test-Time Training","date":"2025-06-05","arxiv_id":"2506.05233","repositories_listed":1,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mesanet-sequence-modeling-by-locally-optimal#ran","syntology_url":"https://syntology.ai/paper/2506.05233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.05233"}},"official":{"repos":["fla-org/flash-linear-attention"],"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/specextend-a-drop-in-enhancement-for","slug":"specextend-a-drop-in-enhancement-for","title":"SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences","date":"2025-05-27","arxiv_id":"2505.20776","repositories_listed":1,"syntology":null},{"url":"/paper/can-compressed-llms-truly-act-an-empirical","slug":"can-compressed-llms-truly-act-an-empirical","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","date":"2025-05-26","arxiv_id":"2505.19433","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-compressed-llms-truly-act-an-empirical#ran","syntology_url":"https://syntology.ai/paper/2505.19433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19433"}},"official":{"repos":["pprp/acbench"],"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","unlocated"]}}},{"url":"/paper/minilongbench-the-low-cost-long-context","slug":"minilongbench-the-low-cost-long-context","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","date":"2025-05-26","arxiv_id":"2505.19959","repositories_listed":1,"syntology":null},{"url":"/paper/too-long-didn-t-model-decomposing-llm-long","slug":"too-long-didn-t-model-decomposing-llm-long","title":"Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels","date":"2025-05-20","arxiv_id":"2505.14925","repositories_listed":1,"syntology":null},{"url":"/paper/livelongbench-tackling-long-context","slug":"livelongbench-tackling-long-context","title":"LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams","date":"2025-04-24","arxiv_id":"2504.17366","repositories_listed":1,"syntology":null},{"url":"/paper/longmamba-enhancing-mamba-s-long-context","slug":"longmamba-enhancing-mamba-s-long-context","title":"LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement","date":"2025-04-22","arxiv_id":"2504.16053","repositories_listed":1,"syntology":null},{"url":"/paper/kimi-vl-technical-report","slug":"kimi-vl-technical-report","title":"Kimi-VL Technical Report","date":"2025-04-10","arxiv_id":"2504.07491","repositories_listed":1,"syntology":null},{"url":"/paper/curie-evaluating-llms-on-multitask-scientific","slug":"curie-evaluating-llms-on-multitask-scientific","title":"CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning","date":"2025-03-14","arxiv_id":"2503.13517","repositories_listed":1,"syntology":null},{"url":"/paper/token-weighting-for-long-range-language","slug":"token-weighting-for-long-range-language","title":"Token Weighting for Long-Range Language Modeling","date":"2025-03-12","arxiv_id":"2503.09202","repositories_listed":1,"syntology":null},{"url":"/paper/longprolip-a-probabilistic-vision-language","slug":"longprolip-a-probabilistic-vision-language","title":"LongProLIP: A Probabilistic Vision-Language Model with Long Context Text","date":"2025-03-11","arxiv_id":"2503.08048","repositories_listed":1,"syntology":{"n":16,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":16,"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) · 9 unverified","sample_list":"/paper/longprolip-a-probabilistic-vision-language#ran","syntology_url":"https://syntology.ai/paper/2503.08048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08048"}},"official":{"repos":["naver-ai/prolip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":9,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/self-taught-agentic-long-context","slug":"self-taught-agentic-long-context","title":"Self-Taught Agentic Long Context Understanding","date":"2025-02-21","arxiv_id":"2502.15920","repositories_listed":1,"syntology":null},{"url":"/paper/scalar-scientific-citation-based-live","slug":"scalar-scientific-citation-based-live","title":"SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning","date":"2025-02-19","arxiv_id":"2502.13753","repositories_listed":1,"syntology":null},{"url":"/paper/fino1-on-the-transferability-of-reasoning","slug":"fino1-on-the-transferability-of-reasoning","title":"Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance","date":"2025-02-12","arxiv_id":"2502.08127","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fino1-on-the-transferability-of-reasoning#ran","syntology_url":"https://syntology.ai/paper/2502.08127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.08127"}},"official":{"repos":["the-finai/fino1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmax-a-comprehensive-multilingual","slug":"benchmax-a-comprehensive-multilingual","title":"BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models","date":"2025-02-11","arxiv_id":"2502.07346","repositories_listed":1,"syntology":null},{"url":"/paper/a-training-free-length-extrapolation-approach","slug":"a-training-free-length-extrapolation-approach","title":"A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)","date":"2025-02-04","arxiv_id":"2502.02659","repositories_listed":1,"syntology":null},{"url":"/paper/m-extending-memoryllm-with-scalable-long-term","slug":"m-extending-memoryllm-with-scalable-long-term","title":"M+: Extending MemoryLLM with Scalable Long-Term Memory","date":"2025-02-01","arxiv_id":"2502.00592","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":2,"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/m-extending-memoryllm-with-scalable-long-term#ran","syntology_url":"https://syntology.ai/paper/2502.00592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00592"}},"official":{"repos":["wangyu-ustc/memoryllm"],"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","unlocated"]}}},{"url":"/paper/rulearena-a-benchmark-for-rule-guided","slug":"rulearena-a-benchmark-for-rule-guided","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","date":"2024-12-12","arxiv_id":"2412.08972","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/rulearena-a-benchmark-for-rule-guided#ran","syntology_url":"https://syntology.ai/paper/2412.08972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08972"}},"official":{"repos":["skyriver-2000/rulearena"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/what-is-wrong-with-perplexity-for-long","slug":"what-is-wrong-with-perplexity-for-long","title":"What is Wrong with Perplexity for Long-context Language Modeling?","date":"2024-10-31","arxiv_id":"2410.23771","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/what-is-wrong-with-perplexity-for-long#ran","syntology_url":"https://syntology.ai/paper/2410.23771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23771"}},"official":{"repos":["pku-ml/longppl"],"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":["official"]}}},{"url":"/paper/selecting-influential-samples-for-long","slug":"selecting-influential-samples-for-long","title":"GATEAU: Selecting Influential Samples for Long Context Alignment","date":"2024-10-21","arxiv_id":"2410.15633","repositories_listed":1,"syntology":null},{"url":"/paper/brief-bridging-retrieval-and-inference-for","slug":"brief-bridging-retrieval-and-inference-for","title":"BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression","date":"2024-10-20","arxiv_id":"2410.15277","repositories_listed":1,"syntology":null},{"url":"/paper/hellobench-evaluating-long-text-generation","slug":"hellobench-evaluating-long-text-generation","title":"HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models","date":"2024-09-24","arxiv_id":"2409.16191","repositories_listed":1,"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/hellobench-evaluating-long-text-generation#ran","syntology_url":"https://syntology.ai/paper/2409.16191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16191"}},"official":{"repos":["quehry/hellobench"],"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/mixture-of-in-context-experts-enhance-llms","slug":"mixture-of-in-context-experts-enhance-llms","title":"Mixture of In-Context Experts Enhance LLMs' Long Context Awareness","date":"2024-06-28","arxiv_id":"2406.19598","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mixture-of-in-context-experts-enhance-llms#ran","syntology_url":"https://syntology.ai/paper/2406.19598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19598"}},"official":{"repos":["p1nksnow/moice"],"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/leave-no-document-behind-benchmarking-long","slug":"leave-no-document-behind-benchmarking-long","title":"Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA","date":"2024-06-25","arxiv_id":"2406.17419","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/leave-no-document-behind-benchmarking-long#ran","syntology_url":"https://syntology.ai/paper/2406.17419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17419"}},"official":{"repos":["mozerwang/loong"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/moa-mixture-of-sparse-attention-for-automatic","slug":"moa-mixture-of-sparse-attention-for-automatic","title":"MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression","date":"2024-06-21","arxiv_id":"2406.14909","repositories_listed":1,"syntology":{"n":22,"n_ran":19,"n_constructed":0,"n_ran_checked":10,"n_instrument":9,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"19 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; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/moa-mixture-of-sparse-attention-for-automatic#ran","syntology_url":"https://syntology.ai/paper/2406.14909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14909"}},"official":{"repos":["thu-nics/moa"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-needle-in-a-haystack-benchmarking","slug":"multimodal-needle-in-a-haystack-benchmarking","title":"Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11230","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/multimodal-needle-in-a-haystack-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2406.11230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11230"}},"official":{"repos":["wang-ml-lab/multimodal-needle-in-a-haystack"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/recurrent-context-compression-efficiently","slug":"recurrent-context-compression-efficiently","title":"Recurrent Context Compression: Efficiently Expanding the Context Window of LLM","date":"2024-06-10","arxiv_id":"2406.06110","repositories_listed":1,"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/recurrent-context-compression-efficiently#ran","syntology_url":"https://syntology.ai/paper/2406.06110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06110"}},"official":{"repos":["WUHU-G/RCC_Transformer"],"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/analyzing-temporal-complex-events-with-large","slug":"analyzing-temporal-complex-events-with-large","title":"Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding","date":"2024-06-04","arxiv_id":"2406.02472","repositories_listed":1,"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/analyzing-temporal-complex-events-with-large#ran","syntology_url":"https://syntology.ai/paper/2406.02472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02472"}},"official":{"repos":["Zhihan72/TCELongBench"],"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/from-text-to-pixel-advancing-long-context","slug":"from-text-to-pixel-advancing-long-context","title":"From Text to Pixel: Advancing Long-Context Understanding in MLLMs","date":"2024-05-23","arxiv_id":"2405.14213","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-head-mechanistically-explains-long","slug":"retrieval-head-mechanistically-explains-long","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","date":"2024-04-24","arxiv_id":"2404.15574","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"7 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieval-head-mechanistically-explains-long#ran","syntology_url":"https://syntology.ai/paper/2404.15574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15574"}},"official":{"repos":["nightdessert/retrieval_head"],"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/hierarchical-context-merging-better-long","slug":"hierarchical-context-merging-better-long","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","date":"2024-04-16","arxiv_id":"2404.10308","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":1,"n_ran_checked":7,"n_instrument":5,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":15,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-context-merging-better-long#ran","syntology_url":"https://syntology.ai/paper/2404.10308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10308"}},"official":{"repos":["alinlab/homer"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ada-leval-evaluating-long-context-llms-with","slug":"ada-leval-evaluating-long-context-llms-with","title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","date":"2024-04-09","arxiv_id":"2404.06480","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ada-leval-evaluating-long-context-llms-with#ran","syntology_url":"https://syntology.ai/paper/2404.06480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06480"}},"official":{"repos":["open-compass/ada-leval"],"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":["official"]}}},{"url":"/paper/llava-uhd-an-lmm-perceiving-any-aspect-ratio","slug":"llava-uhd-an-lmm-perceiving-any-aspect-ratio","title":"LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images","date":"2024-03-18","arxiv_id":"2403.11703","repositories_listed":1,"syntology":null},{"url":"/paper/gemini-1-5-unlocking-multimodal-understanding","slug":"gemini-1-5-unlocking-multimodal-understanding","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","date":"2024-03-08","arxiv_id":"2403.05530","repositories_listed":1,"syntology":null},{"url":"/paper/gemini-a-family-of-highly-capable-multimodal-1","slug":"gemini-a-family-of-highly-capable-multimodal-1","title":"Gemini: A Family of Highly Capable Multimodal Models","date":"2023-12-19","arxiv_id":"2312.11805","repositories_listed":1,"syntology":null},{"url":"/paper/marathon-a-race-through-the-realm-of-long","slug":"marathon-a-race-through-the-realm-of-long","title":"Marathon: A Race Through the Realm of Long Context with Large Language Models","date":"2023-12-15","arxiv_id":"2312.09542","repositories_listed":1,"syntology":null},{"url":"/paper/loogle-can-long-context-language-models","slug":"loogle-can-long-context-language-models","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","date":"2023-11-08","arxiv_id":"2311.04939","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/loogle-can-long-context-language-models#ran","syntology_url":"https://syntology.ai/paper/2311.04939","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04939"}},"official":{"repos":["bigai-nlco/loogle"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":null,"slug":"pacellm-brain-inspired-large-language-models","title":"PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding","date":"2025-06-18","arxiv_id":"2506.17310","repositories_listed":0,"syntology":null},{"url":null,"slug":"atlas-learning-to-optimally-memorize-the","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","date":"2025-05-29","arxiv_id":"2505.23735","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-needle-s-in-the-embodied-haystack","title":"Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning","date":"2025-05-22","arxiv_id":"2505.16928","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-evaluation-of-stem-education","title":"Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning","date":"2025-05-16","arxiv_id":"2505.17050","repositories_listed":0,"syntology":null},{"url":null,"slug":"mooscomp-improving-lightweight-long-context","title":"MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores","date":"2025-04-23","arxiv_id":"2504.16786","repositories_listed":0,"syntology":null},{"url":null,"slug":"lift-improving-long-context-understanding-of","title":"LIFT: Improving Long Context Understanding of Large Language Models through Long Input Fine-Tuning","date":"2025-02-20","arxiv_id":"2502.14644","repositories_listed":0,"syntology":null},{"url":null,"slug":"facilitating-long-context-understanding-via","title":"Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning","date":"2025-02-18","arxiv_id":"2502.13127","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-maintain-fundamental-abilities-under","title":"Can LLMs Maintain Fundamental Abilities under KV Cache Compression?","date":"2025-02-04","arxiv_id":"2502.01941","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-code-generation-with-llms-a-multi","title":"Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks","date":"2025-01-11","arxiv_id":"2501.06625","repositories_listed":0,"syntology":null},{"url":null,"slug":"repository-structure-aware-training-makes","title":"Repository Structure-Aware Training Makes SLMs Better Issue Resolver","date":"2024-12-26","arxiv_id":"2412.19031","repositories_listed":0,"syntology":null},{"url":null,"slug":"lift-improving-long-context-understanding","title":"LIFT: Improving Long Context Understanding Through Long Input Fine-Tuning","date":"2024-12-18","arxiv_id":"2412.13626","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-space-models-are-strong-text-rerankers","title":"State Space Models are Strong Text Rerankers","date":"2024-12-18","arxiv_id":"2412.14354","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-effective-is-self-consistency-for-long","title":"How Effective Is Self-Consistency for Long-Context Problems?","date":"2024-11-02","arxiv_id":"2411.01101","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-scientific-reproducibility-through","title":"Enhancing Scientific Reproducibility Through Automated BioCompute Object Creation Using Retrieval-Augmented Generation from Publications","date":"2024-09-23","arxiv_id":"2409.15076","repositories_listed":0,"syntology":null},{"url":null,"slug":"e2llm-encoder-elongated-large-language-models","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","date":"2024-09-10","arxiv_id":"2409.06679","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-or-holistic-understanding-dolce","title":"Retrieval Or Holistic Understanding? Dolce: Differentiate Our Long Context Evaluation Tasks","date":"2024-09-10","arxiv_id":"2409.06338","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-as-efficient-reward","title":"Large Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement Learning","date":"2024-09-04","arxiv_id":"2409.02428","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatqa-2-bridging-the-gap-to-proprietary-llms","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","date":"2024-07-19","arxiv_id":"2407.14482","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-medical-language-models-for","title":"Fine-Tuning Medical Language Models for Enhanced Long-Contextual Understanding and Domain Expertise","date":"2024-07-16","arxiv_id":"2407.11536","repositories_listed":0,"syntology":null},{"url":null,"slug":"anomaly-detection-of-tabular-data-using-llms","title":"Anomaly Detection of Tabular Data Using LLMs","date":"2024-06-24","arxiv_id":"2406.16308","repositories_listed":0,"syntology":null},{"url":null,"slug":"equipping-transformer-with-random-access","title":"Equipping Transformer with Random-Access Reading for Long-Context Understanding","date":"2024-05-21","arxiv_id":"2405.13216","repositories_listed":0,"syntology":null},{"url":"/paper/what-matters-when-building-vision-language","slug":"what-matters-when-building-vision-language","title":"What matters when building vision-language models?","date":"2024-05-03","arxiv_id":"2405.02246","repositories_listed":0,"syntology":null},{"url":null,"slug":"xl-2-bench-a-benchmark-for-extremely-long","title":"XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies","date":"2024-04-08","arxiv_id":"2404.05446","repositories_listed":0,"syntology":null},{"url":"/paper/the-claude-3-model-family-opus-sonnet-haiku","slug":"the-claude-3-model-family-opus-sonnet-haiku","title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","date":"2024-03-04","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-limits-a-survey-of-techniques-to","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","date":"2024-02-03","arxiv_id":"2402.02244","repositories_listed":0,"syntology":null},{"url":"/paper/a-real-world-webagent-with-planning-long","slug":"a-real-world-webagent-with-planning-long","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","date":"2023-07-24","arxiv_id":"2307.12856","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-parallel-context-windows-a","title":"Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration","date":"2023-05-24","arxiv_id":"2305.15262","repositories_listed":0,"syntology":null}],"syntology_records":29,"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":10,"papers_placed":1,"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/long-context-understanding-on-longbench","since_archive":"/sota/long-context-understanding-on-longbench#since-judged","papers_judged":10,"placed":1}]},"papers_where_code_ran":28,"papers_where_code_ran_first_page":"/task/long-context-understanding/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":"ran","page":1,"of":1,"url":"/task/long-context-understanding/papers/ran/1","json":"/task/long-context-understanding/papers/ran/1.json","rows":28}],"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":"802dac699bbfe988e26d29cd5d5beb8272b5764697ba1fc05b4281b9e203f552","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}