{"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/open-domain-question-answering","name":"Open-Domain Question Answering","slug":"open-domain-question-answering","description_markdown":"Open-domain question answering is the task of question answering on open-domain datasets such as Wikipedia.","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":494,"papers_with_code":238,"benchmarks":15,"benchmark_tables_in_archive":15,"benchmark_tables_shown":15,"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":26,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/open-domain-question-answering-on-kilt","slug":"open-domain-question-answering-on-kilt","dataset":"KILT: Natural Questions","dataset_url":"/dataset/kilt","rows_in_archive":16,"metrics":["KILT-EM","R-Prec","Recall@5","EM","F1","KILT-F1"],"first_row_in_archive_order":{"model":"Re2G","paper_title":"Re2G: Retrieve, Rerank, Generate","paper_url":"/paper/re2g-retrieve-rerank-generate-2","paper_date":"2022-07-13","arxiv_id":"2207.06300","code_links":[{"title":"ibm/kgi-slot-filling","url":"https://github.com/ibm/kgi-slot-filling"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/re2g-retrieve-rerank-generate-2#ran","syntology_url":"https://syntology.ai/paper/2207.06300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06300"}},"official":{"repos":["ibm/kgi-slot-filling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/open-domain-question-answering-on-kilt-eli5","slug":"open-domain-question-answering-on-kilt-eli5","dataset":"KILT: ELI5","dataset_url":"/dataset/kilt","rows_in_archive":16,"metrics":["KILT-RL","R-Prec","Recall@5","ROUGE-L","F1","KILT-F1"],"first_row_in_archive_order":{"model":"somebody","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/open-domain-question-answering-on-kilt-2","slug":"open-domain-question-answering-on-kilt-2","dataset":"KILT: TriviaQA","dataset_url":"/dataset/triviaqa","rows_in_archive":15,"metrics":["KILT-EM","R-Prec","Recall@5","EM","F1","KILT-F1"],"first_row_in_archive_order":{"model":"Re2G","paper_title":"Re2G: Retrieve, Rerank, Generate","paper_url":"/paper/re2g-retrieve-rerank-generate-2","paper_date":"2022-07-13","arxiv_id":"2207.06300","code_links":[{"title":"ibm/kgi-slot-filling","url":"https://github.com/ibm/kgi-slot-filling"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/re2g-retrieve-rerank-generate-2#ran","syntology_url":"https://syntology.ai/paper/2207.06300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06300"}},"official":{"repos":["ibm/kgi-slot-filling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/open-domain-question-answering-on-kilt-1","slug":"open-domain-question-answering-on-kilt-1","dataset":"KILT: HotpotQA","dataset_url":"/dataset/kilt","rows_in_archive":14,"metrics":["KILT-EM","R-Prec","Recall@5","EM","F1","KILT-F1"],"first_row_in_archive_order":{"model":"intersect","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/open-domain-question-answering-on-searchqa","slug":"open-domain-question-answering-on-searchqa","dataset":"SearchQA","dataset_url":"/dataset/searchqa","rows_in_archive":14,"metrics":["EM","N-gram F1","Unigram Acc","F1"],"first_row_in_archive_order":{"model":"Cluster-Former (#C=512)","paper_title":"Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding","paper_url":"/paper/cluster-former-clustering-based-sparse","paper_date":"2020-09-13","arxiv_id":"2009.06097","code_links":[],"syntology":null}},{"leaderboard":"/sota/open-domain-question-answering-on-eli5","slug":"open-domain-question-answering-on-eli5","dataset":"ELI5","dataset_url":"/dataset/eli5","rows_in_archive":6,"metrics":["Rouge-L","Rouge-1","Rouge-2"],"first_row_in_archive_order":{"model":"Fourier Transformer","paper_title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","paper_url":"/paper/fourier-transformer-fast-long-range-modeling","paper_date":"2023-05-24","arxiv_id":"2305.15099","code_links":[{"title":"lumia-group/fouriertransformer","url":"https://github.com/lumia-group/fouriertransformer"}],"syntology":null}},{"leaderboard":"/sota/open-domain-question-answering-on-quasar","slug":"open-domain-question-answering-on-quasar","dataset":"Quasar","dataset_url":"/dataset/quasar-1","rows_in_archive":6,"metrics":["EM (Quasar-T)","F1 (Quasar-T)"],"first_row_in_archive_order":{"model":"Evidence Aggregation via R^3 Re-Ranking","paper_title":"Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering","paper_url":"/paper/evidence-aggregation-for-answer-re-ranking-in","paper_date":"2017-11-14","arxiv_id":"1711.05116","code_links":[{"title":"shuohangwang/mprc","url":"https://github.com/shuohangwang/mprc"}],"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"]}}}},{"leaderboard":"/sota/open-domain-question-answering-on-natural","slug":"open-domain-question-answering-on-natural","dataset":"Natural Questions","dataset_url":"/dataset/natural-questions","rows_in_archive":5,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"FiE","paper_title":"0.8% Nyquist computational ghost imaging via non-experimental deep learning","paper_url":"/paper/0-8-nyquist-computational-ghost-imaging-via","paper_date":"2021-08-17","arxiv_id":"2108.07673","code_links":[],"syntology":null}},{"leaderboard":"/sota/open-domain-question-answering-on","slug":"open-domain-question-answering-on","dataset":"WebQuestions","dataset_url":"/dataset/webquestions","rows_in_archive":4,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"UniK-QA","paper_title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","paper_url":"/paper/unified-open-domain-question-answering-with","paper_date":"2020-12-29","arxiv_id":"2012.14610","code_links":[{"title":"facebookresearch/UniK-QA","url":"https://github.com/facebookresearch/UniK-QA"}],"syntology":null}},{"leaderboard":"/sota/open-domain-question-answering-on-squad1-1","slug":"open-domain-question-answering-on-squad1-1","dataset":"SQuAD1.1 dev","dataset_url":"/dataset/squad","rows_in_archive":4,"metrics":["EM"],"first_row_in_archive_order":{"model":"SPARTA","paper_title":"SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval","paper_url":"/paper/sparta-efficient-open-domain-question","paper_date":"2020-09-28","arxiv_id":"2009.13013","code_links":[{"title":"soco-ai/SF-QA","url":"https://github.com/soco-ai/SF-QA"}],"syntology":null}},{"leaderboard":"/sota/open-domain-question-answering-on-squad11","slug":"open-domain-question-answering-on-squad11","dataset":"SQuAD1.1","dataset_url":"/dataset/squad","rows_in_archive":3,"metrics":["EM"],"first_row_in_archive_order":{"model":"DrQA","paper_title":"Reading Wikipedia to Answer Open-Domain Questions","paper_url":"/paper/reading-wikipedia-to-answer-open-domain","paper_date":"2017-03-31","arxiv_id":"1704.00051","code_links":[{"title":"facebookresearch/ParlAI","url":"https://github.com/facebookresearch/ParlAI"},{"title":"facebookresearch/DrQA","url":"https://github.com/facebookresearch/DrQA"},{"title":"hitvoice/DrQA","url":"https://github.com/hitvoice/DrQA"},{"title":"HKUST-KnowComp/MnemonicReader","url":"https://github.com/HKUST-KnowComp/MnemonicReader"},{"title":"xiangyue9607/CliniRC","url":"https://github.com/xiangyue9607/CliniRC"},{"title":"Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-","url":"https://github.com/Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-"},{"title":"iCompass-ai/TunBERT","url":"https://github.com/iCompass-ai/TunBERT"},{"title":"aaronbae/AnaQA","url":"https://github.com/aaronbae/AnaQA"},{"title":"BAJUKA/SQuAD-NLP","url":"https://github.com/BAJUKA/SQuAD-NLP"},{"title":"sachit-n/drqa_doc_reader","url":"https://github.com/sachit-n/drqa_doc_reader"}],"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/reading-wikipedia-to-answer-open-domain#ran","syntology_url":"https://syntology.ai/paper/1704.00051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.00051"}},"official":{"repos":["facebookresearch/DrQA"],"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/open-domain-question-answering-on-dureader","slug":"open-domain-question-answering-on-dureader","dataset":"DuReader","dataset_url":"/dataset/dureader","rows_in_archive":2,"metrics":["EM"],"first_row_in_archive_order":{"model":"ERNIE 2.0 Large","paper_title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","paper_url":"/paper/ernie-20-a-continual-pre-training-framework","paper_date":"2019-07-29","arxiv_id":"1907.12412","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0"},{"title":"PaddlePaddle/ERNIE","url":"https://github.com/PaddlePaddle/ERNIE"},{"title":"DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc.","url":"https://github.com/DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc."}],"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}},"official":{"repos":["PaddlePaddle/ERNIE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/open-domain-question-answering-on-tqa","slug":"open-domain-question-answering-on-tqa","dataset":"TQA","dataset_url":"/dataset/tqa","rows_in_archive":2,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"UniK-QA","paper_title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","paper_url":"/paper/unified-open-domain-question-answering-with","paper_date":"2020-12-29","arxiv_id":"2012.14610","code_links":[{"title":"facebookresearch/UniK-QA","url":"https://github.com/facebookresearch/UniK-QA"}],"syntology":null}},{"leaderboard":"/sota/open-domain-question-answering-on-natural-1","slug":"open-domain-question-answering-on-natural-1","dataset":"Natural Questions (short)","dataset_url":"/dataset/natural-questions","rows_in_archive":1,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"EMDR2","paper_title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","paper_url":"/paper/end-to-end-training-of-multi-document-reader","paper_date":"2021-06-09","arxiv_id":"2106.05346","code_links":[{"title":"DevSinghSachan/emdr2","url":"https://github.com/DevSinghSachan/emdr2"},{"title":"DevSinghSachan/art","url":"https://github.com/DevSinghSachan/art"}],"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/end-to-end-training-of-multi-document-reader#ran","syntology_url":"https://syntology.ai/paper/2106.05346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05346"}},"official":{"repos":["DevSinghSachan/emdr2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]}}}},{"leaderboard":"/sota/open-domain-question-answering-on-triviaqa","slug":"open-domain-question-answering-on-triviaqa","dataset":"TriviaQA","dataset_url":"/dataset/triviaqa","rows_in_archive":1,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"UnitedQA (Hybrid)","paper_title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","paper_url":"/paper/unitedqa-a-hybrid-approach-for-open-domain","paper_date":"2021-01-01","arxiv_id":"2101.00178","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/natural-questions","name":"Natural Questions","full_name":"","num_papers_in_archive":1404},{"url":"/dataset/triviaqa","name":"TriviaQA","full_name":"","num_papers_in_archive":953},{"url":"/dataset/scienceqa","name":"ScienceQA","full_name":"Science Question Answering","num_papers_in_archive":339},{"url":"/dataset/webquestions","name":"WebQuestions","full_name":"","num_papers_in_archive":241},{"url":"/dataset/lama","name":"LAMA","full_name":"LAnguage Model Analysis","num_papers_in_archive":214},{"url":"/dataset/eli5","name":"ELI5","full_name":"ELI5","num_papers_in_archive":158},{"url":"/dataset/squad","name":"SQuAD","full_name":"Stanford Question Answering Dataset","num_papers_in_archive":151},{"url":"/dataset/searchqa","name":"SearchQA","full_name":"","num_papers_in_archive":133},{"url":"/dataset/kilt","name":"KILT","full_name":"KILT Benchmark","num_papers_in_archive":117},{"url":"/dataset/dureader","name":"DuReader","full_name":"","num_papers_in_archive":65},{"url":"/dataset/quasar-t","name":"QUASAR-T","full_name":"QUestion Answering by Search And Reading – Trivia","num_papers_in_archive":55},{"url":"/dataset/qrecc","name":"QReCC","full_name":"","num_papers_in_archive":51},{"url":"/dataset/mkqa","name":"MKQA","full_name":"Multilingual Knowledge Questions and Answers","num_papers_in_archive":49},{"url":"/dataset/tqa","name":"TQA","full_name":"Textbook Question Answering","num_papers_in_archive":48},{"url":"/dataset/quasar-1","name":"QUASAR","full_name":"QUestion Answering by Search And Reading","num_papers_in_archive":47},{"url":"/dataset/break","name":"BREAK","full_name":"BREAK","num_papers_in_archive":39},{"url":"/dataset/wikimovies","name":"WikiMovies","full_name":"","num_papers_in_archive":39},{"url":"/dataset/infoseek","name":"InfoSeek","full_name":"Visual Information Seeking","num_papers_in_archive":36},{"url":"/dataset/arcd","name":"ARCD","full_name":"","num_papers_in_archive":24},{"url":"/dataset/oven","name":"OVEN","full_name":"Open-domain Visual Entity Recognition","num_papers_in_archive":19},{"url":"/dataset/qampari","name":"QAMPARI","full_name":"","num_papers_in_archive":19},{"url":"/dataset/xqa","name":"XQA","full_name":"XQA","num_papers_in_archive":6},{"url":"/dataset/simran-arora","name":"ConcurrentQA Benchmark","full_name":"","num_papers_in_archive":3},{"url":"/dataset/crepe","name":"CREPE","full_name":"","num_papers_in_archive":2},{"url":"/dataset/coresearch","name":"CoreSearch","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wikiqaar","name":"WikiQAar","full_name":"English-Arabic Wikipedia Question-Answering","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"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":5,"rows_per_page":100,"shown":100,"of":494,"of_with_code":238,"tagged_in_all":494,"counts":{"archive_papers_tagged":494,"with_a_code_link":238,"where_syntology_ran_a_sample":80,"not_listed_spam_title":0,"listed":494,"listed_where_code_ran":80,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":68,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":68,"listed_every_run_a_failure_of_syntologys_instrument":12,"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/bart-denoising-sequence-to-sequence-pre","slug":"bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","repositories_listed":47,"syntology":{"n":53,"n_ran":40,"n_constructed":7,"n_ran_checked":30,"n_instrument":10,"n_unverified":13,"n_honours":1,"n_violates":2,"n_no_contract":27,"n_pointer_only":13,"phrase":"40 ran (of which 7 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 2 violated, 27 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/bart-denoising-sequence-to-sequence-pre#ran","syntology_url":"https://syntology.ai/paper/1910.13461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13461"}},"official":null}},{"url":"/paper/bidirectional-attention-flow-for-machine","slug":"bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","arxiv_id":"1611.01603","repositories_listed":27,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bidirectional-attention-flow-for-machine#ran","syntology_url":"https://syntology.ai/paper/1611.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01603"}},"official":{"repos":["allenai/bi-att-flow"],"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":["listed","official"]}}},{"url":"/paper/dense-passage-retrieval-for-open-domain","slug":"dense-passage-retrieval-for-open-domain","title":"Dense Passage Retrieval for Open-Domain Question Answering","date":"2020-04-10","arxiv_id":"2004.04906","repositories_listed":19,"syntology":{"n":14,"n_ran":11,"n_constructed":6,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":9,"phrase":"11 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dense-passage-retrieval-for-open-domain#ran","syntology_url":"https://syntology.ai/paper/2004.04906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04906"}},"official":{"repos":["facebookresearch/DPR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/reformer-the-efficient-transformer-1","slug":"reformer-the-efficient-transformer-1","title":"Reformer: The Efficient Transformer","date":"2020-01-13","arxiv_id":"2001.04451","repositories_listed":10,"syntology":{"n":8,"n_ran":6,"n_constructed":1,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/reformer-the-efficient-transformer-1#ran","syntology_url":"https://syntology.ai/paper/2001.04451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04451"}},"official":{"repos":["google/trax"],"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/reading-wikipedia-to-answer-open-domain","slug":"reading-wikipedia-to-answer-open-domain","title":"Reading Wikipedia to Answer Open-Domain Questions","date":"2017-03-31","arxiv_id":"1704.00051","repositories_listed":10,"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/reading-wikipedia-to-answer-open-domain#ran","syntology_url":"https://syntology.ai/paper/1704.00051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.00051"}},"official":{"repos":["facebookresearch/DrQA"],"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/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/190410509","slug":"190410509","title":"Generating Long Sequences with Sparse Transformers","date":"2019-04-23","arxiv_id":"1904.10509","repositories_listed":7,"syntology":{"n":6,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/190410509#ran","syntology_url":"https://syntology.ai/paper/1904.10509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.10509"}},"official":{"repos":["openai/sparse_attention"],"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/realm-retrieval-augmented-language-model-pre","slug":"realm-retrieval-augmented-language-model-pre","title":"REALM: Retrieval-Augmented Language Model Pre-Training","date":"2020-02-10","arxiv_id":"2002.08909","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/realm-retrieval-augmented-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2002.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.08909"}},"official":{"repos":["google-research/language"],"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/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","repositories_listed":6,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}},"official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"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/reducing-transformer-depth-on-demand-with-1","slug":"reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","date":"2019-09-25","arxiv_id":"1909.11556","repositories_listed":5,"syntology":null},{"url":"/paper/learning-discrete-representations-via-1","slug":"learning-discrete-representations-via-1","title":"Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval","date":"2021-10-12","arxiv_id":"2110.05789","repositories_listed":4,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":2,"phrase":"16 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; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/learning-discrete-representations-via-1#ran","syntology_url":"https://syntology.ai/paper/2110.05789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.05789"}},"official":{"repos":["jingtaozhan/repconc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-dense-representations-of-phrases-at","slug":"learning-dense-representations-of-phrases-at","title":"Learning Dense Representations of Phrases at Scale","date":"2020-12-23","arxiv_id":"2012.12624","repositories_listed":4,"syntology":null},{"url":"/paper/distilling-knowledge-from-reader-to-retriever-1","slug":"distilling-knowledge-from-reader-to-retriever-1","title":"Distilling Knowledge from Reader to Retriever for Question Answering","date":"2020-12-08","arxiv_id":"2012.04584","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distilling-knowledge-from-reader-to-retriever-1#ran","syntology_url":"https://syntology.ai/paper/2012.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04584"}},"official":{"repos":["facebookresearch/FiD"],"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/ktrain-a-low-code-library-for-augmented","slug":"ktrain-a-low-code-library-for-augmented","title":"ktrain: A Low-Code Library for Augmented Machine Learning","date":"2020-04-19","arxiv_id":"2004.10703","repositories_listed":4,"syntology":{"n":16,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/ktrain-a-low-code-library-for-augmented#ran","syntology_url":"https://syntology.ai/paper/2004.10703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.10703"}},"official":{"repos":["amaiya/ktrain"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":10,"ran_from_kinds":["listed"]}}},{"url":"/paper/break-it-down-a-question-understanding","slug":"break-it-down-a-question-understanding","title":"Break It Down: A Question Understanding Benchmark","date":"2020-01-31","arxiv_id":"2001.11770","repositories_listed":4,"syntology":null},{"url":"/paper/gated-attention-readers-for-text","slug":"gated-attention-readers-for-text","title":"Gated-Attention Readers for Text Comprehension","date":"2016-06-05","arxiv_id":"1606.01549","repositories_listed":4,"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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gated-attention-readers-for-text#ran","syntology_url":"https://syntology.ai/paper/1606.01549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.01549"}},"official":{"repos":["bdhingra/ga-reader"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/colbertv2-effective-and-efficient-retrieval","slug":"colbertv2-effective-and-efficient-retrieval","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","date":"2021-12-02","arxiv_id":"2112.01488","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":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colbertv2-effective-and-efficient-retrieval#ran","syntology_url":"https://syntology.ai/paper/2112.01488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01488"}},"official":{"repos":["stanford-futuredata/ColBERT"],"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/answer-complex-questions-path-ranker-is-all","slug":"answer-complex-questions-path-ranker-is-all","title":"Answer Complex Questions: Path Ranker Is All You Need","date":"2021-07-11","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/narrative-question-answering-with-cutting","slug":"narrative-question-answering-with-cutting","title":"Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study","date":"2021-06-07","arxiv_id":"2106.03826","repositories_listed":3,"syntology":null},{"url":"/paper/what-makes-good-in-context-examples-for-gpt-3","slug":"what-makes-good-in-context-examples-for-gpt-3","title":"What Makes Good In-Context Examples for GPT-$3$?","date":"2021-01-17","arxiv_id":"2101.06804","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":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-makes-good-in-context-examples-for-gpt-3#ran","syntology_url":"https://syntology.ai/paper/2101.06804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06804"}},"official":null}},{"url":"/paper/what-disease-does-this-patient-have-a-large","slug":"what-disease-does-this-patient-have-a-large","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","date":"2020-09-28","arxiv_id":"2009.13081","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/what-disease-does-this-patient-have-a-large#ran","syntology_url":"https://syntology.ai/paper/2009.13081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13081"}},"official":{"repos":["jind11/MedQA"],"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/kilt-a-benchmark-for-knowledge-intensive","slug":"kilt-a-benchmark-for-knowledge-intensive","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","date":"2020-09-04","arxiv_id":"2009.02252","repositories_listed":3,"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/kilt-a-benchmark-for-knowledge-intensive#ran","syntology_url":"https://syntology.ai/paper/2009.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.02252"}},"official":{"repos":["facebookresearch/KILT"],"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/contextualized-sparse-representation-with-1","slug":"contextualized-sparse-representation-with-1","title":"Contextualized Sparse Representations for Real-Time Open-Domain Question Answering","date":"2019-11-07","arxiv_id":"1911.02896","repositories_listed":3,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":6,"n_honours":5,"n_violates":2,"n_no_contract":2,"n_pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/contextualized-sparse-representation-with-1#ran","syntology_url":"https://syntology.ai/paper/1911.02896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02896"}},"official":{"repos":["jhyuklee/sparc"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/ernie-20-a-continual-pre-training-framework#ran","syntology_url":"https://syntology.ai/paper/1907.12412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12412"}},"official":{"repos":["PaddlePaddle/ERNIE"],"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/eli5-long-form-question-answering","slug":"eli5-long-form-question-answering","title":"ELI5: Long Form Question Answering","date":"2019-07-22","arxiv_id":"1907.09190","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eli5-long-form-question-answering#ran","syntology_url":"https://syntology.ai/paper/1907.09190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09190"}},"official":{"repos":["facebookresearch/ELI5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/190600300","slug":"190600300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","date":"2019-06-01","arxiv_id":"1906.00300","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-attend-on-essential-terms-an","slug":"learning-to-attend-on-essential-terms-an","title":"Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering","date":"2018-08-28","arxiv_id":"1808.09492","repositories_listed":3,"syntology":null},{"url":"/paper/searchqa-a-new-qa-dataset-augmented-with","slug":"searchqa-a-new-qa-dataset-augmented-with","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","date":"2017-04-18","arxiv_id":"1704.05179","repositories_listed":3,"syntology":null},{"url":"/paper/webwalker-benchmarking-llms-in-web-traversal","slug":"webwalker-benchmarking-llms-in-web-traversal","title":"WebWalker: Benchmarking LLMs in Web Traversal","date":"2025-01-13","arxiv_id":"2501.07572","repositories_listed":2,"syntology":null},{"url":"/paper/w-rag-weakly-supervised-dense-retrieval-in","slug":"w-rag-weakly-supervised-dense-retrieval-in","title":"W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering","date":"2024-08-15","arxiv_id":"2408.08444","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-filter-context-for-retrieval","slug":"learning-to-filter-context-for-retrieval","title":"Learning to Filter Context for Retrieval-Augmented Generation","date":"2023-11-14","arxiv_id":"2311.08377","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-filter-context-for-retrieval#ran","syntology_url":"https://syntology.ai/paper/2311.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08377"}},"official":{"repos":["zorazrw/filco"],"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/recomp-improving-retrieval-augmented-lms-with","slug":"recomp-improving-retrieval-augmented-lms-with","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","date":"2023-10-06","arxiv_id":"2310.04408","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/recomp-improving-retrieval-augmented-lms-with#ran","syntology_url":"https://syntology.ai/paper/2310.04408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04408"}},"official":{"repos":["carriex/recomp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/making-retrieval-augmented-language-models","slug":"making-retrieval-augmented-language-models","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","date":"2023-10-02","arxiv_id":"2310.01558","repositories_listed":2,"syntology":null},{"url":"/paper/conformal-language-modeling","slug":"conformal-language-modeling","title":"Conformal Language Modeling","date":"2023-06-16","arxiv_id":"2306.10193","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/conformal-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2306.10193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.10193"}},"official":{"repos":["varal7/conformal-language-modeling"],"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/expand-rerank-and-retrieve-query-reranking","slug":"expand-rerank-and-retrieve-query-reranking","title":"Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering","date":"2023-05-26","arxiv_id":"2305.17080","repositories_listed":2,"syntology":null},{"url":"/paper/can-pre-trained-vision-and-language-models","slug":"can-pre-trained-vision-and-language-models","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","date":"2023-02-23","arxiv_id":"2302.11713","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-pre-trained-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2302.11713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11713"}},"official":{"repos":["edchengg/infoseek_eval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/open-domain-question-answering-via-chain-of","slug":"open-domain-question-answering-via-chain-of","title":"Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge","date":"2022-10-22","arxiv_id":"2210.12338","repositories_listed":2,"syntology":null},{"url":"/paper/variational-open-domain-question-answering","slug":"variational-open-domain-question-answering","title":"Variational Open-Domain Question Answering","date":"2022-09-23","arxiv_id":"2210.06345","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/variational-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/2210.06345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06345"}},"official":{"repos":["findzebra/fz-openqa","VodLM/vod"],"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/generate-rather-than-retrieve-large-language","slug":"generate-rather-than-retrieve-large-language","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","date":"2022-09-21","arxiv_id":"2209.10063","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generate-rather-than-retrieve-large-language#ran","syntology_url":"https://syntology.ai/paper/2209.10063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.10063"}},"official":{"repos":["wyu97/GenRead"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-learning-with-retrieval-augmented","slug":"few-shot-learning-with-retrieval-augmented","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","date":"2022-08-05","arxiv_id":"2208.03299","repositories_listed":2,"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/few-shot-learning-with-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2208.03299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03299"}},"official":{"repos":["facebookresearch/atlas"],"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/lepus-prompt-based-unsupervised-multi-hop","slug":"lepus-prompt-based-unsupervised-multi-hop","title":"Few-shot Reranking for Multi-hop QA via Language Model Prompting","date":"2022-05-25","arxiv_id":"2205.12650","repositories_listed":2,"syntology":null},{"url":"/paper/qampari-an-open-domain-question-answering","slug":"qampari-an-open-domain-question-answering","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","date":"2022-05-25","arxiv_id":"2205.12665","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/qampari-an-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/2205.12665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12665"}},"official":null}},{"url":"/paper/salient-phrase-aware-dense-retrieval-can-a","slug":"salient-phrase-aware-dense-retrieval-can-a","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","date":"2021-10-13","arxiv_id":"2110.06918","repositories_listed":2,"syntology":null},{"url":"/paper/entqa-entity-linking-as-question-answering","slug":"entqa-entity-linking-as-question-answering","title":"EntQA: Entity Linking as Question Answering","date":"2021-10-05","arxiv_id":"2110.02369","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":3,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entqa-entity-linking-as-question-answering#ran","syntology_url":"https://syntology.ai/paper/2110.02369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02369"}},"official":{"repos":["wenzhengzhang/entqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dealing-with-typos-for-bert-based-passage","slug":"dealing-with-typos-for-bert-based-passage","title":"Dealing with Typos for BERT-based Passage Retrieval and Ranking","date":"2021-08-27","arxiv_id":"2108.12139","repositories_listed":2,"syntology":null},{"url":"/paper/fine-tune-the-entire-rag-architecture","slug":"fine-tune-the-entire-rag-architecture","title":"Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering","date":"2021-06-22","arxiv_id":"2106.11517","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-training-of-multi-document-reader","slug":"end-to-end-training-of-multi-document-reader","title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","date":"2021-06-09","arxiv_id":"2106.05346","repositories_listed":2,"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/end-to-end-training-of-multi-document-reader#ran","syntology_url":"https://syntology.ai/paper/2106.05346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05346"}},"official":{"repos":["DevSinghSachan/emdr2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/hurdles-to-progress-in-long-form-question","slug":"hurdles-to-progress-in-long-form-question","title":"Hurdles to Progress in Long-form Question Answering","date":"2021-03-10","arxiv_id":"2103.06332","repositories_listed":2,"syntology":null},{"url":"/paper/pruning-the-index-contents-for-memory","slug":"pruning-the-index-contents-for-memory","title":"Pruning the Index Contents for Memory Efficient Open-Domain QA","date":"2021-02-21","arxiv_id":"2102.10697","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":2,"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: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pruning-the-index-contents-for-memory#ran","syntology_url":"https://syntology.ai/paper/2102.10697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.10697"}},"official":{"repos":["KNOT-FIT-BUT/R2-D2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"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/open-domain-question-answering-goes","slug":"open-domain-question-answering-goes","title":"Open-Domain Question Answering Goes Conversational via Question Rewriting","date":"2020-10-10","arxiv_id":"2010.04898","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-domain-question-answering-goes#ran","syntology_url":"https://syntology.ai/paper/2010.04898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04898"}},"official":{"repos":["apple/ml-qrecc"],"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/autoregressive-entity-retrieval","slug":"autoregressive-entity-retrieval","title":"Autoregressive Entity Retrieval","date":"2020-10-02","arxiv_id":"2010.00904","repositories_listed":2,"syntology":null},{"url":"/paper/mkqa-a-linguistically-diverse-benchmark-for","slug":"mkqa-a-linguistically-diverse-benchmark-for","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","date":"2020-07-30","arxiv_id":"2007.15207","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mkqa-a-linguistically-diverse-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2007.15207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15207"}},"official":{"repos":["apple/ml-mkqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ambigqa-answering-ambiguous-open-domain","slug":"ambigqa-answering-ambiguous-open-domain","title":"AmbigQA: Answering Ambiguous Open-domain Questions","date":"2020-04-22","arxiv_id":"2004.10645","repositories_listed":2,"syntology":null},{"url":"/paper/what-does-my-qa-model-know-devising","slug":"what-does-my-qa-model-know-devising","title":"What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge","date":"2019-12-31","arxiv_id":"1912.13337","repositories_listed":2,"syntology":null},{"url":"/paper/densely-connected-attention-propagation-for","slug":"densely-connected-attention-propagation-for","title":"Densely Connected Attention Propagation for Reading Comprehension","date":"2018-11-10","arxiv_id":"1811.04210","repositories_listed":2,"syntology":null},{"url":"/paper/open-domain-question-answering-using-early","slug":"open-domain-question-answering-using-early","title":"Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text","date":"2018-09-04","arxiv_id":"1809.00782","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-domain-question-answering-using-early#ran","syntology_url":"https://syntology.ai/paper/1809.00782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.00782"}},"official":{"repos":["OceanskySun/GraftNet"],"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/text-understanding-with-the-attention-sum","slug":"text-understanding-with-the-attention-sum","title":"Text Understanding with the Attention Sum Reader Network","date":"2016-03-04","arxiv_id":"1603.01547","repositories_listed":2,"syntology":{"n":10,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 8 unverified","sample_list":"/paper/text-understanding-with-the-attention-sum#ran","syntology_url":"https://syntology.ai/paper/1603.01547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.01547"}},"official":{"repos":["rkadlec/asreader"],"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/deep-learning-for-answer-sentence-selection","slug":"deep-learning-for-answer-sentence-selection","title":"Deep Learning for Answer Sentence Selection","date":"2014-12-04","arxiv_id":"1412.1632","repositories_listed":2,"syntology":null},{"url":"/paper/tablerag-a-retrieval-augmented-generation","slug":"tablerag-a-retrieval-augmented-generation","title":"TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning","date":"2025-06-12","arxiv_id":"2506.10380","repositories_listed":1,"syntology":null},{"url":"/paper/ecorag-evidentiality-guided-compression-for","slug":"ecorag-evidentiality-guided-compression-for","title":"ECoRAG: Evidentiality-guided Compression for Long Context RAG","date":"2025-06-05","arxiv_id":"2506.05167","repositories_listed":1,"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/nover-incentive-training-for-language-models","slug":"nover-incentive-training-for-language-models","title":"NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning","date":"2025-05-21","arxiv_id":"2505.16022","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11140","slug":"2505-11140","title":"Scaling Reasoning can Improve Factuality in Large Language Models","date":"2025-05-16","arxiv_id":"2505.11140","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-llm-based-relevance-judgment","slug":"benchmarking-llm-based-relevance-judgment","title":"Benchmarking LLM-based Relevance Judgment Methods","date":"2025-04-17","arxiv_id":"2504.12558","repositories_listed":1,"syntology":null},{"url":"/paper/dense-passage-retrieval-in-conversational","slug":"dense-passage-retrieval-in-conversational","title":"Dense Passage Retrieval in Conversational Search","date":"2025-03-21","arxiv_id":"2503.17507","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-multilingual-open-domain-qa-from-5","slug":"few-shot-multilingual-open-domain-qa-from-5","title":"Few-Shot Multilingual Open-Domain QA from 5 Examples","date":"2025-02-27","arxiv_id":"2502.19722","repositories_listed":1,"syntology":null},{"url":"/paper/ra-mtr-a-retrieval-augmented-multi-task","slug":"ra-mtr-a-retrieval-augmented-multi-task","title":"RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents","date":"2025-02-17","arxiv_id":"2502.12124","repositories_listed":1,"syntology":null},{"url":"/paper/talk-structurally-act-hierarchically-a","slug":"talk-structurally-act-hierarchically-a","title":"Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems","date":"2025-02-16","arxiv_id":"2502.11098","repositories_listed":1,"syntology":null},{"url":"/paper/context-awareness-gate-for-retrieval","slug":"context-awareness-gate-for-retrieval","title":"Context Awareness Gate For Retrieval Augmented Generation","date":"2024-11-25","arxiv_id":"2411.16133","repositories_listed":1,"syntology":null},{"url":"/paper/steering-knowledge-selection-behaviours-in","slug":"steering-knowledge-selection-behaviours-in","title":"Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering","date":"2024-10-21","arxiv_id":"2410.15999","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/retriever-and-memory-towards-adaptive-note","slug":"retriever-and-memory-towards-adaptive-note","title":"Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation","date":"2024-10-11","arxiv_id":"2410.08821","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retriever-and-memory-towards-adaptive-note#ran","syntology_url":"https://syntology.ai/paper/2410.08821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08821"}},"official":{"repos":["thunlp/adaptive-note"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/does-rag-introduce-unfairness-in-llms","slug":"does-rag-introduce-unfairness-in-llms","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","date":"2024-09-29","arxiv_id":"2409.19804","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/does-rag-introduce-unfairness-in-llms#ran","syntology_url":"https://syntology.ai/paper/2409.19804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19804"}},"official":{"repos":["elviswxy/rag_fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/detecting-temporal-ambiguity-in-questions","slug":"detecting-temporal-ambiguity-in-questions","title":"Detecting Temporal Ambiguity in Questions","date":"2024-09-25","arxiv_id":"2409.17046","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/entropy-based-decoding-for-retrieval","slug":"entropy-based-decoding-for-retrieval","title":"Entropy-Based Decoding for Retrieval-Augmented Large Language Models","date":"2024-06-25","arxiv_id":"2406.17519","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-query-and-passage-for-retrieval","slug":"augmenting-query-and-passage-for-retrieval","title":"QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs","date":"2024-06-20","arxiv_id":"2406.14277","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/augmenting-query-and-passage-for-retrieval#ran","syntology_url":"https://syntology.ai/paper/2406.14277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14277"}},"official":{"repos":["kmswin1/qpaug"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/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/passage-specific-prompt-tuning-for-passage","slug":"passage-specific-prompt-tuning-for-passage","title":"Passage-specific Prompt Tuning for Passage Reranking in Question Answering with Large Language Models","date":"2024-05-31","arxiv_id":"2405.20654","repositories_listed":1,"syntology":null},{"url":"/paper/unraveling-and-mitigating-retriever","slug":"unraveling-and-mitigating-retriever","title":"Unraveling and Mitigating Retriever Inconsistencies in Retrieval-Augmented Large Language Models","date":"2024-05-31","arxiv_id":"2405.20680","repositories_listed":1,"syntology":null},{"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/tanq-an-open-domain-dataset-of-table-answered","slug":"tanq-an-open-domain-dataset-of-table-answered","title":"TANQ: An open domain dataset of table answered questions","date":"2024-05-13","arxiv_id":"2405.07765","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-contextual-understanding-in-large","slug":"enhancing-contextual-understanding-in-large","title":"Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding","date":"2024-05-04","arxiv_id":"2405.02750","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/enhancing-contextual-understanding-in-large#ran","syntology_url":"https://syntology.ai/paper/2405.02750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02750"}},"official":{"repos":["amazon-science/contextualunderstanding-contrastivedecoding"],"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/semi-parametric-retrieval-via-binary-token","slug":"semi-parametric-retrieval-via-binary-token","title":"Semi-Parametric Retrieval via Binary Bag-of-Tokens Index","date":"2024-05-03","arxiv_id":"2405.01924","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-search-engine-for-machines-unified","slug":"towards-a-search-engine-for-machines-unified","title":"Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models","date":"2024-04-30","arxiv_id":"2405.00175","repositories_listed":1,"syntology":null},{"url":"/paper/when-to-retrieve-teaching-llms-to-utilize","slug":"when-to-retrieve-teaching-llms-to-utilize","title":"When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively","date":"2024-04-30","arxiv_id":"2404.19705","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":3,"n_violates":2,"n_no_contract":0,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/when-to-retrieve-teaching-llms-to-utilize#ran","syntology_url":"https://syntology.ai/paper/2404.19705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19705"}},"official":{"repos":["tLabruna/Adapt-LLM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spiral-of-silences-how-is-large-language","slug":"spiral-of-silences-how-is-large-language","title":"Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering","date":"2024-04-16","arxiv_id":"2404.10496","repositories_listed":1,"syntology":null},{"url":"/paper/kazqad-kazakh-open-domain-question-answering","slug":"kazqad-kazakh-open-domain-question-answering","title":"KazQAD: Kazakh Open-Domain Question Answering Dataset","date":"2024-04-06","arxiv_id":"2404.04487","repositories_listed":1,"syntology":null},{"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/improving-retrieval-augmented-open-domain","slug":"improving-retrieval-augmented-open-domain","title":"Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts","date":"2024-04-02","arxiv_id":"2404.02022","repositories_listed":1,"syntology":null},{"url":"/paper/arabicaqa-a-comprehensive-dataset-for-arabic","slug":"arabicaqa-a-comprehensive-dataset-for-arabic","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","date":"2024-03-26","arxiv_id":"2403.17848","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/arabicaqa-a-comprehensive-dataset-for-arabic#ran","syntology_url":"https://syntology.ai/paper/2403.17848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17848"}},"official":{"repos":["datascienceuibk/arabicaqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/denoising-table-text-retrieval-for-open","slug":"denoising-table-text-retrieval-for-open","title":"Denoising Table-Text Retrieval for Open-Domain Question Answering","date":"2024-03-26","arxiv_id":"2403.17611","repositories_listed":1,"syntology":null},{"url":"/paper/blended-rag-improving-rag-retriever-augmented","slug":"blended-rag-improving-rag-retriever-augmented","title":"Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers","date":"2024-03-22","arxiv_id":"2404.07220","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":2,"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/blended-rag-improving-rag-retriever-augmented#ran","syntology_url":"https://syntology.ai/paper/2404.07220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07220"}},"official":{"repos":["ibm-ecosystem-engineering/blended-rag"],"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/imagination-augmented-generation-learning-to","slug":"imagination-augmented-generation-learning-to","title":"Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering","date":"2024-03-22","arxiv_id":"2403.15268","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":3,"n_pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/imagination-augmented-generation-learning-to#ran","syntology_url":"https://syntology.ai/paper/2403.15268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15268"}},"official":{"repos":["xnhyacinth/iag"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/desire-me-domain-enhanced-supervised","slug":"desire-me-domain-enhanced-supervised","title":"DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts","date":"2024-03-20","arxiv_id":"2403.13468","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-memorization-the-challenge-of-random","slug":"beyond-memorization-the-challenge-of-random","title":"Beyond Memorization: The Challenge of Random Memory Access in Language Models","date":"2024-03-12","arxiv_id":"2403.07805","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/beyond-memorization-the-challenge-of-random#ran","syntology_url":"https://syntology.ai/paper/2403.07805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07805"}},"official":{"repos":["sail-sg/lm-random-memory-access"],"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"]}}}],"syntology_records":47,"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":8,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/open-domain-question-answering-on-searchqa","since_archive":"/sota/open-domain-question-answering-on-searchqa#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/open-domain-question-answering-on-eli5","since_archive":"/sota/open-domain-question-answering-on-eli5#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/open-domain-question-answering-on-natural","since_archive":"/sota/open-domain-question-answering-on-natural#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/open-domain-question-answering-on-squad1-1","since_archive":"/sota/open-domain-question-answering-on-squad1-1#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/open-domain-question-answering-on-squad11","since_archive":"/sota/open-domain-question-answering-on-squad11#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/open-domain-question-answering-on-triviaqa","since_archive":"/sota/open-domain-question-answering-on-triviaqa#since-judged","papers_judged":6,"placed":0}]},"papers_where_code_ran":80,"papers_where_code_ran_first_page":"/task/open-domain-question-answering/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":5,"url":"/task/open-domain-question-answering/papers/2","json":"/task/open-domain-question-answering/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/open-domain-question-answering/papers/3","json":"/task/open-domain-question-answering/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/open-domain-question-answering/papers/4","json":"/task/open-domain-question-answering/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/open-domain-question-answering/papers/5","json":"/task/open-domain-question-answering/papers/5.json","rows":94},{"order":"ran","page":1,"of":1,"url":"/task/open-domain-question-answering/papers/ran/1","json":"/task/open-domain-question-answering/papers/ran/1.json","rows":80}],"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":"e34610cb8ad2e11737229051ed07ea3d5b59fb26f411590776c6fe98bbc41f3c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}