{"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/triviaqa","name":"TriviaQA","slug":"triviaqa","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":124,"papers_with_code":60,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/triviaqa-on-big-bench","slug":"triviaqa-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Gopher-280B (few-shot, k=64)","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_url":"/paper/scaling-language-models-methods-analysis-1","paper_date":"2021-12-08","arxiv_id":"2112.11446","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"syntology":null}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[{"url":"/task/general-knowledge","name":"General Knowledge"}],"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":2,"rows_per_page":100,"shown":100,"of":124,"of_with_code":60,"tagged_in_all":124,"counts":{"archive_papers_tagged":124,"with_a_code_link":60,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":124,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/longformer-the-long-document-transformer","slug":"longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","arxiv_id":"2004.05150","repositories_listed":22,"syntology":{"n":35,"n_ran":22,"n_constructed":4,"n_ran_checked":14,"n_instrument":8,"n_unverified":13,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":5,"phrase":"22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/longformer-the-long-document-transformer#ran","syntology_url":"https://syntology.ai/paper/2004.05150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05150"}},"official":{"repos":["allenai/longformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/leveraging-passage-retrieval-with-generative","slug":"leveraging-passage-retrieval-with-generative","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","date":"2020-07-02","arxiv_id":"2007.01282","repositories_listed":8,"syntology":null},{"url":"/paper/knowledge-guided-text-retrieval-and-reading","slug":"knowledge-guided-text-retrieval-and-reading","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","date":"2019-11-10","arxiv_id":"1911.03868","repositories_listed":7,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/knowledge-guided-text-retrieval-and-reading#ran","syntology_url":"https://syntology.ai/paper/1911.03868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03868"}},"official":null}},{"url":"/paper/relevance-guided-supervision-for-openqa-with","slug":"relevance-guided-supervision-for-openqa-with","title":"Relevance-guided Supervision for OpenQA with ColBERT","date":"2020-07-01","arxiv_id":"2007.00814","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/relevance-guided-supervision-for-openqa-with#ran","syntology_url":"https://syntology.ai/paper/2007.00814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00814"}},"official":{"repos":["stanford-futuredata/ColBERT","stanfordnlp/ColBERT-QA"],"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/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/triviaqa-a-large-scale-distantly-supervised","slug":"triviaqa-a-large-scale-distantly-supervised","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","date":"2017-05-09","arxiv_id":"1705.03551","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/triviaqa-a-large-scale-distantly-supervised#ran","syntology_url":"https://syntology.ai/paper/1705.03551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.03551"}},"official":null}},{"url":"/paper/lacie-listener-aware-finetuning-for","slug":"lacie-listener-aware-finetuning-for","title":"LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models","date":"2024-05-31","arxiv_id":"2405.21028","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-training-of-neural-retrievers-for","slug":"end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","repositories_listed":2,"syntology":null},{"url":"/paper/genki-enhancing-open-domain-question","slug":"genki-enhancing-open-domain-question","title":"GenKI: Enhancing Open-Domain Question Answering with Knowledge Integration and Controllable Generation in Large Language Models","date":"2025-05-26","arxiv_id":"2505.19660","repositories_listed":1,"syntology":null},{"url":"/paper/dragonverseqa-open-domain-long-form-context","slug":"dragonverseqa-open-domain-long-form-context","title":"DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering","date":"2024-12-21","arxiv_id":"2412.16694","repositories_listed":1,"syntology":null},{"url":"/paper/kv-prediction-for-improved-time-to-first","slug":"kv-prediction-for-improved-time-to-first","title":"KV Prediction for Improved Time to First Token","date":"2024-10-10","arxiv_id":"2410.08391","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-hint-generation-approaches-in-open","slug":"exploring-hint-generation-approaches-in-open","title":"Exploring Hint Generation Approaches in Open-Domain Question Answering","date":"2024-09-24","arxiv_id":"2409.16096","repositories_listed":1,"syntology":null},{"url":"/paper/fastfid-improve-inference-efficiency-of-open","slug":"fastfid-improve-inference-efficiency-of-open","title":"FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection","date":"2024-08-12","arxiv_id":"2408.06333","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/fastfid-improve-inference-efficiency-of-open#ran","syntology_url":"https://syntology.ai/paper/2408.06333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06333"}},"official":{"repos":["thunlp/fastfid"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/from-artificial-needles-to-real-haystacks","slug":"from-artificial-needles-to-real-haystacks","title":"From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data","date":"2024-06-27","arxiv_id":"2406.19292","repositories_listed":1,"syntology":null},{"url":"/paper/judging-the-judges-evaluating-alignment-and","slug":"judging-the-judges-evaluating-alignment-and","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","date":"2024-06-18","arxiv_id":"2406.12624","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":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/judging-the-judges-evaluating-alignment-and#ran","syntology_url":"https://syntology.ai/paper/2406.12624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12624"}},"official":{"repos":["UMass-Meta-LLM-Eval/llm_eval"],"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/cram-credibility-aware-attention-modification","slug":"cram-credibility-aware-attention-modification","title":"CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG","date":"2024-06-17","arxiv_id":"2406.11497","repositories_listed":1,"syntology":null},{"url":"/paper/re-rag-improving-open-domain-qa-performance","slug":"re-rag-improving-open-domain-qa-performance","title":"RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05794","repositories_listed":1,"syntology":null},{"url":"/paper/retaining-key-information-under-high","slug":"retaining-key-information-under-high","title":"Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs","date":"2024-06-04","arxiv_id":"2406.02376","repositories_listed":1,"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/retaining-key-information-under-high#ran","syntology_url":"https://syntology.ai/paper/2406.02376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02376"}},"official":{"repos":["DeepLearnXMU/QGC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/accurate-and-nuanced-open-qa-evaluation","slug":"accurate-and-nuanced-open-qa-evaluation","title":"Accurate and Nuanced Open-QA Evaluation Through Textual Entailment","date":"2024-05-26","arxiv_id":"2405.16702","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/accurate-and-nuanced-open-qa-evaluation#ran","syntology_url":"https://syntology.ai/paper/2405.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16702"}},"official":{"repos":["U-Alberta/QA-partial-marks"],"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/layer-skip-enabling-early-exit-inference-and","slug":"layer-skip-enabling-early-exit-inference-and","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","date":"2024-04-25","arxiv_id":"2404.16710","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/layer-skip-enabling-early-exit-inference-and#ran","syntology_url":"https://syntology.ai/paper/2404.16710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16710"}},"official":{"repos":["facebookresearch/layerskip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-granularity-guided-fusion-in-decoder","slug":"multi-granularity-guided-fusion-in-decoder","title":"Multi-Granularity Guided Fusion-in-Decoder","date":"2024-04-03","arxiv_id":"2404.02581","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-multi-role-capabilities-of-large","slug":"harnessing-multi-role-capabilities-of-large","title":"Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering","date":"2024-03-08","arxiv_id":"2403.05217","repositories_listed":1,"syntology":null},{"url":"/paper/unfamiliar-finetuning-examples-control-how","slug":"unfamiliar-finetuning-examples-control-how","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","date":"2024-03-08","arxiv_id":"2403.05612","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unfamiliar-finetuning-examples-control-how#ran","syntology_url":"https://syntology.ai/paper/2403.05612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05612"}},"official":{"repos":["katiekang1998/llm_hallucinations"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-bias-variance-covariance-decomposition-of","slug":"a-bias-variance-covariance-decomposition-of","title":"A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models","date":"2023-10-09","arxiv_id":"2310.05833","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"5 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-bias-variance-covariance-decomposition-of#ran","syntology_url":"https://syntology.ai/paper/2310.05833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05833"}},"official":{"repos":["mlo-lab/bvcd_generative_models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/generator-retriever-generator-a-novel","slug":"generator-retriever-generator-a-novel","title":"Generator-Retriever-Generator Approach for Open-Domain Question Answering","date":"2023-07-21","arxiv_id":"2307.11278","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-abstract-meaning-representation","slug":"exploiting-abstract-meaning-representation","title":"Exploiting Abstract Meaning Representation for Open-Domain Question Answering","date":"2023-05-26","arxiv_id":"2305.17050","repositories_listed":1,"syntology":null},{"url":"/paper/rfid-towards-rational-fusion-in-decoder-for","slug":"rfid-towards-rational-fusion-in-decoder-for","title":"RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering","date":"2023-05-26","arxiv_id":"2305.17041","repositories_listed":1,"syntology":null},{"url":"/paper/beamsearchqa-large-language-models-are-strong","slug":"beamsearchqa-large-language-models-are-strong","title":"Allies: Prompting Large Language Model with Beam Search","date":"2023-05-24","arxiv_id":"2305.14766","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/beamsearchqa-large-language-models-are-strong#ran","syntology_url":"https://syntology.ai/paper/2305.14766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14766"}},"official":{"repos":["microsoft/simxns"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/just-ask-for-calibration-strategies-for","slug":"just-ask-for-calibration-strategies-for","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","date":"2023-05-24","arxiv_id":"2305.14975","repositories_listed":1,"syntology":null},{"url":"/paper/critic-large-language-models-can-self-correct","slug":"critic-large-language-models-can-self-correct","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","date":"2023-05-19","arxiv_id":"2305.11738","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/critic-large-language-models-can-self-correct#ran","syntology_url":"https://syntology.ai/paper/2305.11738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11738"}},"official":{"repos":["microsoft/ProphetNet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-struggle-to-learn-long","slug":"large-language-models-struggle-to-learn-long","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","date":"2022-11-15","arxiv_id":"2211.08411","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-struggle-to-learn-long#ran","syntology_url":"https://syntology.ai/paper/2211.08411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08411"}},"official":{"repos":["nkandpa2/long_tail_knowledge"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/recitation-augmented-language-models","slug":"recitation-augmented-language-models","title":"Recitation-Augmented Language Models","date":"2022-10-04","arxiv_id":"2210.01296","repositories_listed":1,"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/recitation-augmented-language-models#ran","syntology_url":"https://syntology.ai/paper/2210.01296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01296"}},"official":{"repos":["edward-sun/recite"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-question-answering-via-answer","slug":"unsupervised-question-answering-via-answer","title":"Unsupervised Question Answering via Answer Diversifying","date":"2022-08-23","arxiv_id":"2208.10813","repositories_listed":1,"syntology":null},{"url":"/paper/a-neural-corpus-indexer-for-document","slug":"a-neural-corpus-indexer-for-document","title":"A Neural Corpus Indexer for Document Retrieval","date":"2022-06-06","arxiv_id":"2206.02743","repositories_listed":1,"syntology":null},{"url":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","repositories_listed":1,"syntology":{"n":14,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}},"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/text-and-code-embeddings-by-contrastive-pre","slug":"text-and-code-embeddings-by-contrastive-pre","title":"Text and Code Embeddings by Contrastive Pre-Training","date":"2022-01-24","arxiv_id":"2201.10005","repositories_listed":1,"syntology":null},{"url":"/paper/whats-in-a-name-answer-equivalence-for-open","slug":"whats-in-a-name-answer-equivalence-for-open","title":"What’s in a Name? Answer Equivalence For Open-Domain Question Answering","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-retriever-ranker-for-dense-text","slug":"adversarial-retriever-ranker-for-dense-text","title":"Adversarial Retriever-Ranker for dense text retrieval","date":"2021-10-07","arxiv_id":"2110.03611","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/adversarial-retriever-ranker-for-dense-text#ran","syntology_url":"https://syntology.ai/paper/2110.03611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03611"}},"official":{"repos":["microsoft/ar2"],"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":"/paper/what-s-in-a-name-answer-equivalence-for-open","slug":"what-s-in-a-name-answer-equivalence-for-open","title":"What's in a Name? Answer Equivalence For Open-Domain Question Answering","date":"2021-09-11","arxiv_id":"2109.05289","repositories_listed":1,"syntology":null},{"url":"/paper/ror-read-over-read-for-long-document-machine","slug":"ror-read-over-read-for-long-document-machine","title":"RoR: Read-over-Read for Long Document Machine Reading Comprehension","date":"2021-09-10","arxiv_id":"2109.04780","repositories_listed":1,"syntology":null},{"url":"/paper/r2-d2-a-modular-baseline-for-open-domain","slug":"r2-d2-a-modular-baseline-for-open-domain","title":"R2-D2: A Modular Baseline for Open-Domain Question Answering","date":"2021-09-08","arxiv_id":"2109.03502","repositories_listed":1,"syntology":null},{"url":"/paper/challenges-in-generalization-in-open-domain","slug":"challenges-in-generalization-in-open-domain","title":"Challenges in Generalization in Open Domain Question Answering","date":"2021-09-02","arxiv_id":"2109.01156","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-passage-retrieval-with-hashing-for","slug":"efficient-passage-retrieval-with-hashing-for","title":"Efficient Passage Retrieval with Hashing for Open-domain Question Answering","date":"2021-06-02","arxiv_id":"2106.00882","repositories_listed":1,"syntology":null},{"url":"/paper/reader-guided-passage-reranking-for-open","slug":"reader-guided-passage-reranking-for-open","title":"Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering","date":"2021-01-01","arxiv_id":"2101.00294","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reader-guided-passage-reranking-for-open#ran","syntology_url":"https://syntology.ai/paper/2101.00294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00294"}},"official":{"repos":["morningmoni/GAR"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-memory-efficient-baseline-for-open-domain","slug":"a-memory-efficient-baseline-for-open-domain","title":"A Memory Efficient Baseline for Open Domain Question Answering","date":"2020-12-30","arxiv_id":"2012.15156","repositories_listed":1,"syntology":null},{"url":"/paper/answering-ambiguous-questions-through","slug":"answering-ambiguous-questions-through","title":"Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction","date":"2020-11-26","arxiv_id":"2011.13137","repositories_listed":1,"syntology":null},{"url":"/paper/reconsider-re-ranking-using-span-focused","slug":"reconsider-re-ranking-using-span-focused","title":"RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering","date":"2020-10-21","arxiv_id":"2010.10757","repositories_listed":1,"syntology":null},{"url":"/paper/generation-augmented-retrieval-for-open","slug":"generation-augmented-retrieval-for-open","title":"Generation-Augmented Retrieval for Open-domain Question Answering","date":"2020-09-17","arxiv_id":"2009.08553","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-chunking-mechanisms-for-long-text","slug":"recurrent-chunking-mechanisms-for-long-text","title":"Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension","date":"2020-05-16","arxiv_id":"2005.08056","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-assumptions-matter-improved","slug":"probabilistic-assumptions-matter-improved","title":"Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering","date":"2020-05-05","arxiv_id":"2005.01898","repositories_listed":1,"syntology":null},{"url":"/paper/entities-as-experts-sparse-memory-access-with","slug":"entities-as-experts-sparse-memory-access-with","title":"Entities as Experts: Sparse Memory Access with Entity Supervision","date":"2020-04-15","arxiv_id":"2004.07202","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/entities-as-experts-sparse-memory-access-with#ran","syntology_url":"https://syntology.ai/paper/2004.07202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07202"}},"official":null}},{"url":"/paper/a-discrete-hard-em-approach-for-weakly","slug":"a-discrete-hard-em-approach-for-weakly","title":"A Discrete Hard EM Approach for Weakly Supervised Question Answering","date":"2019-09-11","arxiv_id":"1909.04849","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-discrete-hard-em-approach-for-weakly#ran","syntology_url":"https://syntology.ai/paper/1909.04849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04849"}},"official":{"repos":["shmsw25/qa-hard-em"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieve-read-rerank-towards-end-to-end-multi","slug":"retrieve-read-rerank-towards-end-to-end-multi","title":"Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension","date":"2019-06-11","arxiv_id":"1906.04618","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieve-read-rerank-towards-end-to-end-multi#ran","syntology_url":"https://syntology.ai/paper/1906.04618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04618"}},"official":{"repos":["huminghao16/RE3QA"],"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/multi-step-retriever-reader-interaction-for-1","slug":"multi-step-retriever-reader-interaction-for-1","title":"Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering","date":"2019-05-14","arxiv_id":"1905.05733","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"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, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-step-retriever-reader-interaction-for-1#ran","syntology_url":"https://syntology.ai/paper/1905.05733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05733"}},"official":{"repos":["rajarshd/Multi-Step-Reasoning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/episodic-memory-reader-learning-what-to","slug":"episodic-memory-reader-learning-what-to","title":"Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data","date":"2019-03-14","arxiv_id":"1903.06164","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-hierarchical-attention","slug":"multi-granularity-hierarchical-attention","title":"Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering","date":"2018-11-29","arxiv_id":"1811.11934","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-and-robust-question-answering-from","slug":"efficient-and-robust-question-answering-from","title":"Efficient and Robust Question Answering from Minimal Context over Documents","date":"2018-05-21","arxiv_id":"1805.08092","repositories_listed":1,"syntology":null},{"url":"/paper/a-question-focused-multi-factor-attention","slug":"a-question-focused-multi-factor-attention","title":"A Question-Focused Multi-Factor Attention Network for Question Answering","date":"2018-01-25","arxiv_id":"1801.08290","repositories_listed":1,"syntology":null},{"url":"/paper/evidence-aggregation-for-answer-re-ranking-in","slug":"evidence-aggregation-for-answer-re-ranking-in","title":"Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering","date":"2017-11-14","arxiv_id":"1711.05116","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evidence-aggregation-for-answer-re-ranking-in#ran","syntology_url":"https://syntology.ai/paper/1711.05116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.05116"}},"official":{"repos":["shuohangwang/mprc"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/simple-and-effective-multi-paragraph-reading","slug":"simple-and-effective-multi-paragraph-reading","title":"Simple and Effective Multi-Paragraph Reading Comprehension","date":"2017-10-29","arxiv_id":"1710.10723","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/simple-and-effective-multi-paragraph-reading#ran","syntology_url":"https://syntology.ai/paper/1710.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10723"}},"official":{"repos":["allenai/document-qa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":null,"slug":"2506-03100","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","date":"2025-06-03","arxiv_id":"2506.03100","repositories_listed":0,"syntology":null},{"url":null,"slug":"hash-rag-bridging-deep-hashing-with-retriever","title":"HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16133","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11271","title":"Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models","date":"2025-05-16","arxiv_id":"2505.11271","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamax-dynamic-computing-for-transformers","title":"DYNAMAX: Dynamic computing for Transformers and Mamba based architectures","date":"2025-04-29","arxiv_id":"2504.20922","repositories_listed":0,"syntology":null},{"url":null,"slug":"shed-hd-a-shannon-entropy-distribution","title":"ShED-HD: A Shannon Entropy Distribution Framework for Lightweight Hallucination Detection on Edge Devices","date":"2025-03-23","arxiv_id":"2503.18242","repositories_listed":0,"syntology":null},{"url":null,"slug":"cachefocus-dynamic-cache-re-positioning-for","title":"CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation","date":"2025-02-16","arxiv_id":"2502.11101","repositories_listed":0,"syntology":null},{"url":null,"slug":"cost-saving-llm-cascades-with-early","title":"Cost-Saving LLM Cascades with Early Abstention","date":"2025-02-13","arxiv_id":"2502.09054","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-training-large-language-models-for-tool","title":"Self-Training Large Language Models for Tool-Use Without Demonstrations","date":"2025-02-09","arxiv_id":"2502.05867","repositories_listed":0,"syntology":null},{"url":"/paper/vision-centric-token-compression-in-large","slug":"vision-centric-token-compression-in-large","title":"Vision-centric Token Compression in Large Language Model","date":"2025-02-02","arxiv_id":"2502.00791","repositories_listed":0,"syntology":{"n":9,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vision-centric-token-compression-in-large#ran","syntology_url":"https://syntology.ai/paper/2502.00791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00791"}},"official":null}},{"url":null,"slug":"asrank-zero-shot-re-ranking-with-answer-scent","title":"ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval","date":"2025-01-25","arxiv_id":"2501.15245","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-generated-and-retrieved-knowledge","title":"Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation","date":"2024-12-25","arxiv_id":"2412.18800","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-importance-and-hallucination-analysis","title":"Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity","date":"2024-11-15","arxiv_id":"2411.10069","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-uncertainty-in-llms-to-enhance","title":"Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI","date":"2024-11-04","arxiv_id":"2411.02381","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-data-synthesis-a-teacher-model","title":"Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation","date":"2024-10-27","arxiv_id":"2410.20362","repositories_listed":0,"syntology":null},{"url":null,"slug":"sfr-rag-towards-contextually-faithful-llms","title":"SFR-RAG: Towards Contextually Faithful LLMs","date":"2024-09-16","arxiv_id":"2409.09916","repositories_listed":0,"syntology":null},{"url":null,"slug":"speculative-rag-enhancing-retrieval-augmented","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","date":"2024-07-11","arxiv_id":"2407.08223","repositories_listed":0,"syntology":null},{"url":null,"slug":"ks-llm-knowledge-selection-of-large-language","title":"KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering","date":"2024-04-24","arxiv_id":"2404.15660","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-llm-hallucinations-via-conformal","title":"Mitigating LLM Hallucinations via Conformal Abstention","date":"2024-04-04","arxiv_id":"2405.01563","repositories_listed":0,"syntology":null},{"url":null,"slug":"fit-rag-black-box-rag-with-factual","title":"FIT-RAG: Black-Box RAG with Factual Information and Token Reduction","date":"2024-03-21","arxiv_id":"2403.14374","repositories_listed":0,"syntology":null},{"url":"/paper/researchy-questions-a-dataset-of-multi","slug":"researchy-questions-a-dataset-of-multi","title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","date":"2024-02-27","arxiv_id":"2402.17896","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-self-endorsement-improves","title":"Fine-Grained Self-Endorsement Improves Factuality and Reasoning","date":"2024-02-23","arxiv_id":"2402.15631","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-generative-ai-paradox-on-evaluation-what","title":"The Generative AI Paradox on Evaluation: What It Can Solve, It May Not Evaluate","date":"2024-02-09","arxiv_id":"2402.06204","repositories_listed":0,"syntology":null},{"url":null,"slug":"attendre-wait-to-attend-by-retrieval-with","title":"Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing","date":"2024-01-10","arxiv_id":"2401.04881","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-transformer-knowledge-distillation","title":"Efficient Transformer Knowledge Distillation: A Performance Review","date":"2023-11-22","arxiv_id":"2311.13657","repositories_listed":0,"syntology":null},{"url":null,"slug":"noisy-pair-corrector-for-dense-retrieval","title":"Noisy Pair Corrector for Dense Retrieval","date":"2023-11-07","arxiv_id":"2311.03798","repositories_listed":0,"syntology":null},{"url":null,"slug":"sorted-llama-unlocking-the-potential-of","title":"Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference","date":"2023-09-16","arxiv_id":"2309.08968","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-to-read-documents-or-qa-history-on","title":"When to Read Documents or QA History: On Unified and Selective Open-domain QA","date":"2023-06-07","arxiv_id":"2306.04176","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-sparse-retrieval-using-sparse-language","title":"Dense Sparse Retrieval: Using Sparse Language Models for Inference Efficient Dense Retrieval","date":"2023-03-31","arxiv_id":"2304.00114","repositories_listed":0,"syntology":null},{"url":null,"slug":"quick-dense-retrievers-consume-kale-post","title":"Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders","date":"2023-03-31","arxiv_id":"2304.01016","repositories_listed":0,"syntology":null},{"url":null,"slug":"clam-selective-clarification-for-ambiguous","title":"CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models","date":"2022-12-15","arxiv_id":"2212.07769","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-open-domain-qa-reader-utilize-external","title":"Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?","date":"2022-11-23","arxiv_id":"2211.12707","repositories_listed":0,"syntology":null},{"url":"/paper/fie-building-a-global-probability-space-by","slug":"fie-building-a-global-probability-space-by","title":"FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering","date":"2022-11-18","arxiv_id":"2211.10147","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-structured-knowledge-infusion-for-large","title":"SKILL: Structured Knowledge Infusion for Large Language Models","date":"2022-05-17","arxiv_id":"2205.08184","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-copy-augmented-generative-model-for-open-1","title":"A Copy-Augmented Generative Model for Open-Domain Question Answering","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gnn-encoder-learning-a-dual-encoder","title":"GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval","date":"2022-04-18","arxiv_id":"2204.08241","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-understanding-based-multi-document","title":"Deep Understanding based Multi-Document Machine Reading Comprehension","date":"2022-02-25","arxiv_id":"2204.03494","repositories_listed":0,"syntology":null},{"url":null,"slug":"grow-and-clip-informative-yet-concise","title":"Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation","date":"2022-01-13","arxiv_id":"2201.05088","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-need-one-model-for-open-domain","title":"You Only Need One Model for Open-domain Question Answering","date":"2021-12-14","arxiv_id":"2112.07381","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-copy-augmented-generative-model-for-open","title":"A Copy-Augmented Generative Model for Open-Domain Question Answering","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-in-generalization-in-open-domain-1","title":"Challenges in Generalization in Open Domain Question Answering","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":25,"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":24,"papers_where_code_ran_first_page":"/task/triviaqa/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":2,"url":"/task/triviaqa/papers/2","json":"/task/triviaqa/papers/2.json","rows":24},{"order":"ran","page":1,"of":1,"url":"/task/triviaqa/papers/ran/1","json":"/task/triviaqa/papers/ran/1.json","rows":24}],"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":"2bc5babf8d560a094eea609f6eab19022a92f1b44de21978601db6c14a6908a0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}