{"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/extractive-question-answering","name":"Extractive Question-Answering","slug":"extractive-question-answering","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":102,"papers_with_code":44,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/codequeries","name":"CodeQueries","full_name":"","num_papers_in_archive":2},{"url":"/dataset/m2qa","name":"M2QA","full_name":"Multi-domain Multilingual Question Answering","num_papers_in_archive":2},{"url":"/dataset/hr-extractive-question-answering","name":"HR Extractive Question Answering","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":102,"of_with_code":44,"tagged_in_all":102,"counts":{"archive_papers_tagged":102,"with_a_code_link":44,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":102,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/luke-deep-contextualized-entity","slug":"luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","repositories_listed":9,"syntology":{"n":10,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 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) · 7 unverified","sample_list":"/paper/luke-deep-contextualized-entity#ran","syntology_url":"https://syntology.ai/paper/2010.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01057"}},"official":{"repos":["studio-ousia/luke"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mlqa-evaluating-cross-lingual-extractive","slug":"mlqa-evaluating-cross-lingual-extractive","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","date":"2019-10-16","arxiv_id":"1910.07475","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mlqa-evaluating-cross-lingual-extractive#ran","syntology_url":"https://syntology.ai/paper/1910.07475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07475"}},"official":{"repos":["facebookresearch/MLQA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-generate-instruction-tuning","slug":"learning-to-generate-instruction-tuning","title":"Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation","date":"2024-02-28","arxiv_id":"2402.18334","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/covid-19-event-extraction-from-twitter-via","slug":"covid-19-event-extraction-from-twitter-via","title":"COVID-19 event extraction from Twitter via extractive question answering with continuous prompts","date":"2023-03-19","arxiv_id":"2303.10659","repositories_listed":2,"syntology":null},{"url":"/paper/can-explanations-be-useful-for-calibrating","slug":"can-explanations-be-useful-for-calibrating","title":"Can Explanations Be Useful for Calibrating Black Box Models?","date":"2021-10-14","arxiv_id":"2110.07586","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/can-explanations-be-useful-for-calibrating#ran","syntology_url":"https://syntology.ai/paper/2110.07586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07586"}},"official":{"repos":["xiye17/interpcalib"],"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/on-the-multilingual-capabilities-of-very","slug":"on-the-multilingual-capabilities-of-very","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","date":"2021-08-30","arxiv_id":"2108.13349","repositories_listed":2,"syntology":null},{"url":"/paper/spanish-language-models","slug":"spanish-language-models","title":"MarIA: Spanish Language Models","date":"2021-07-15","arxiv_id":"2107.07253","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/learning-recurrent-span-representations-for","slug":"learning-recurrent-span-representations-for","title":"Learning Recurrent Span Representations for Extractive Question Answering","date":"2016-11-04","arxiv_id":"1611.01436","repositories_listed":2,"syntology":null},{"url":"/paper/synfintabs-a-dataset-of-synthetic-financial","slug":"synfintabs-a-dataset-of-synthetic-financial","title":"SynFinTabs: A Dataset of Synthetic Financial Tables for Information and Table Extraction","date":"2024-12-05","arxiv_id":"2412.04262","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-extractive-question-answering","slug":"towards-robust-extractive-question-answering","title":"Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology","date":"2024-09-29","arxiv_id":"2409.19766","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-language-model-generalization-in","slug":"exploring-language-model-generalization-in","title":"Exploring Language Model Generalization in Low-Resource Extractive QA","date":"2024-09-27","arxiv_id":"2409.18446","repositories_listed":1,"syntology":null},{"url":"/paper/can-a-multichoice-dataset-be-repurposed-for","slug":"can-a-multichoice-dataset-be-repurposed-for","title":"From Multiple-Choice to Extractive QA: A Case Study for English and Arabic","date":"2024-04-26","arxiv_id":"2404.17342","repositories_listed":1,"syntology":null},{"url":"/paper/quality-quantity-synthetic-corpora-from","slug":"quality-quantity-synthetic-corpora-from","title":"TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering","date":"2023-10-25","arxiv_id":"2310.16995","repositories_listed":1,"syntology":null},{"url":"/paper/promoting-generalized-cross-lingual-question","slug":"promoting-generalized-cross-lingual-question","title":"Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge Distillation","date":"2023-09-29","arxiv_id":"2309.17134","repositories_listed":1,"syntology":null},{"url":"/paper/catfood-counterfactual-augmented-training-for","slug":"catfood-counterfactual-augmented-training-for","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","date":"2023-09-14","arxiv_id":"2309.07822","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/catfood-counterfactual-augmented-training-for#ran","syntology_url":"https://syntology.ai/paper/2309.07822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07822"}},"official":{"repos":["ukplab/catfood"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/agent-a-novel-pipeline-for-automatically","slug":"agent-a-novel-pipeline-for-automatically","title":"AGent: A Novel Pipeline for Automatically Creating Unanswerable Questions","date":"2023-09-10","arxiv_id":"2309.05103","repositories_listed":1,"syntology":null},{"url":"/paper/multi-source-test-time-adaptation-as-dueling","slug":"multi-source-test-time-adaptation-as-dueling","title":"Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering","date":"2023-06-11","arxiv_id":"2306.06779","repositories_listed":1,"syntology":null},{"url":"/paper/continually-improving-extractive-qa-via-human","slug":"continually-improving-extractive-qa-via-human","title":"Continually Improving Extractive QA via Human Feedback","date":"2023-05-21","arxiv_id":"2305.12473","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-loose-optimization-for-robust","slug":"adaptive-loose-optimization-for-robust","title":"Adaptive loose optimization for robust question answering","date":"2023-05-06","arxiv_id":"2305.03971","repositories_listed":1,"syntology":null},{"url":"/paper/brent-bidirectional-retrieval-enhanced","slug":"brent-bidirectional-retrieval-enhanced","title":"BRENT: Bidirectional Retrieval Enhanced Norwegian Transformer","date":"2023-04-19","arxiv_id":"2304.09649","repositories_listed":1,"syntology":null},{"url":"/paper/can-bert-refrain-from-forgetting-on","slug":"can-bert-refrain-from-forgetting-on","title":"Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study","date":"2023-03-02","arxiv_id":"2303.01081","repositories_listed":1,"syntology":null},{"url":"/paper/tokenization-consistency-matters-for","slug":"tokenization-consistency-matters-for","title":"Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks","date":"2022-12-19","arxiv_id":"2212.09912","repositories_listed":1,"syntology":null},{"url":"/paper/from-clozing-to-comprehending-retrofitting","slug":"from-clozing-to-comprehending-retrofitting","title":"From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader","date":"2022-12-09","arxiv_id":"2212.04755","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 2 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) · 1 unverified","sample_list":"/paper/from-clozing-to-comprehending-retrofitting#ran","syntology_url":"https://syntology.ai/paper/2212.04755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04755"}},"official":{"repos":["damo-nlp-sg/pmr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dyrex-dynamic-query-representation-for","slug":"dyrex-dynamic-query-representation-for","title":"DyREx: Dynamic Query Representation for Extractive Question Answering","date":"2022-10-26","arxiv_id":"2210.15048","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/dyrex-dynamic-query-representation-for#ran","syntology_url":"https://syntology.ai/paper/2210.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15048"}},"official":{"repos":["urchade/dyrex"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/findings-of-the-vardial-evaluation-campaign-2","slug":"findings-of-the-vardial-evaluation-campaign-2","title":"Findings of the VarDial Evaluation Campaign 2022","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-answer-semantic-queries-over-code","slug":"learning-to-answer-semantic-queries-over-code","title":"CodeQueries: A Dataset of Semantic Queries over Code","date":"2022-09-17","arxiv_id":"2209.08372","repositories_listed":1,"syntology":null},{"url":"/paper/kecp-knowledge-enhanced-contrastive-prompting","slug":"kecp-knowledge-enhanced-contrastive-prompting","title":"KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering","date":"2022-05-06","arxiv_id":"2205.03071","repositories_listed":1,"syntology":null},{"url":"/paper/science-checker-extractive-boolean-question","slug":"science-checker-extractive-boolean-question","title":"Science Checker: Extractive-Boolean Question Answering For Scientific Fact Checking","date":"2022-04-26","arxiv_id":"2204.12263","repositories_listed":1,"syntology":null},{"url":"/paper/xqa-dst-multi-domain-and-multi-lingual-1","slug":"xqa-dst-multi-domain-and-multi-lingual-1","title":"XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking","date":"2022-04-12","arxiv_id":"2204.05895","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-bandit-learning-from-user-feedback-1","slug":"simulating-bandit-learning-from-user-feedback-1","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","date":"2022-03-18","arxiv_id":"2203.10079","repositories_listed":1,"syntology":null},{"url":"/paper/block-skim-efficient-question-answering-for","slug":"block-skim-efficient-question-answering-for","title":"Block-Skim: Efficient Question Answering for Transformer","date":"2021-12-16","arxiv_id":"2112.08560","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-search-as-extractive-paraphrase-span-1","slug":"semantic-search-as-extractive-paraphrase-span-1","title":"Semantic Search as Extractive Paraphrase Span Detection","date":"2021-12-09","arxiv_id":"2112.04886","repositories_listed":1,"syntology":null},{"url":"/paper/a-few-more-examples-may-be-worth-billions-of","slug":"a-few-more-examples-may-be-worth-billions-of","title":"A Few More Examples May Be Worth Billions of Parameters","date":"2021-10-08","arxiv_id":"2110.04374","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":5,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-few-more-examples-may-be-worth-billions-of#ran","syntology_url":"https://syntology.ai/paper/2110.04374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04374"}},"official":{"repos":["yuvalkirstain/lm-evaluation-harness"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reasonbert-pre-trained-to-reason-with-distant","slug":"reasonbert-pre-trained-to-reason-with-distant","title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","date":"2021-09-10","arxiv_id":"2109.04912","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/reasonbert-pre-trained-to-reason-with-distant#ran","syntology_url":"https://syntology.ai/paper/2109.04912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04912"}},"official":{"repos":["sunlab-osu/reasonbert"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/how-optimal-is-greedy-decoding-for-extractive","slug":"how-optimal-is-greedy-decoding-for-extractive","title":"How Optimal is Greedy Decoding for Extractive Question Answering?","date":"2021-08-12","arxiv_id":"2108.05857","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/how-optimal-is-greedy-decoding-for-extractive#ran","syntology_url":"https://syntology.ai/paper/2108.05857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05857"}},"official":{"repos":["ocastel/exact-extract"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-tagging-for-biomedical-extractive","slug":"sequence-tagging-for-biomedical-extractive","title":"Sequence tagging for biomedical extractive question answering","date":"2021-04-15","arxiv_id":"2104.07535","repositories_listed":1,"syntology":null},{"url":"/paper/cooperative-learning-of-zero-shot-machine","slug":"cooperative-learning-of-zero-shot-machine","title":"Cooperative Self-training of Machine Reading Comprehension","date":"2021-03-12","arxiv_id":"2103.07449","repositories_listed":1,"syntology":null},{"url":"/paper/improving-qa-generalization-by-concurrent","slug":"improving-qa-generalization-by-concurrent","title":"Improving QA Generalization by Concurrent Modeling of Multiple Biases","date":"2020-10-07","arxiv_id":"2010.03338","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-objectives-of-extractive","slug":"rethinking-the-objectives-of-extractive","title":"Rethinking the Objectives of Extractive Question Answering","date":"2020-08-28","arxiv_id":"2008.12804","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-the-objectives-of-extractive#ran","syntology_url":"https://syntology.ai/paper/2008.12804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.12804"}},"official":{"repos":["KNOT-FIT-BUT/JointSpanExtraction"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/look-at-the-first-sentence-position-bias-in","slug":"look-at-the-first-sentence-position-bias-in","title":"Look at the First Sentence: Position Bias in Question Answering","date":"2020-04-30","arxiv_id":"2004.14602","repositories_listed":1,"syntology":null},{"url":"/paper/gendered-pronoun-resolution-using-bert-and-an","slug":"gendered-pronoun-resolution-using-bert-and-an","title":"Gendered Pronoun Resolution using BERT and an extractive question answering formulation","date":"2019-06-09","arxiv_id":"1906.03695","repositories_listed":1,"syntology":null},{"url":null,"slug":"hallumix-a-task-agnostic-multi-domain","title":"HalluMix: A Task-Agnostic, Multi-Domain Benchmark for Real-World Hallucination Detection","date":"2025-05-01","arxiv_id":"2505.00506","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-dataset-cartography-ineffective-using","title":"When is dataset cartography ineffective? Using training dynamics does not improve robustness against Adversarial SQuAD","date":"2025-03-24","arxiv_id":"2503.18290","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-mechanistic-circuits-for-extractive","title":"On Mechanistic Circuits for Extractive Question-Answering","date":"2025-02-12","arxiv_id":"2502.08059","repositories_listed":0,"syntology":null},{"url":null,"slug":"foqa-a-faroese-question-answering-dataset","title":"FoQA: A Faroese Question-Answering Dataset","date":"2025-02-11","arxiv_id":"2502.07642","repositories_listed":0,"syntology":null},{"url":null,"slug":"amasquad-a-benchmark-for-amharic-extractive","title":"AmaSQuAD: A Benchmark for Amharic Extractive Question Answering","date":"2025-02-04","arxiv_id":"2502.02047","repositories_listed":0,"syntology":null},{"url":null,"slug":"passage-segmentation-of-documents-for","title":"Passage Segmentation of Documents for Extractive Question Answering","date":"2025-01-17","arxiv_id":"2501.09940","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-defer-for-extractive-question","title":"Learning-to-Defer for Extractive Question Answering","date":"2024-10-21","arxiv_id":"2410.15761","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-sparql-and-llms-for-question","title":"Integrating SPARQL and LLMs for Question Answering over Scholarly Data Sources","date":"2024-09-11","arxiv_id":"2409.18969","repositories_listed":0,"syntology":null},{"url":null,"slug":"omos-qa-a-dataset-for-cross-lingual","title":"OMoS-QA: A Dataset for Cross-Lingual Extractive Question Answering in a German Migration Context","date":"2024-07-22","arxiv_id":"2407.15736","repositories_listed":0,"syntology":null},{"url":null,"slug":"clinical-reading-comprehension-with-encoder","title":"Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization","date":"2024-07-19","arxiv_id":"2407.14000","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlkd-bert-multi-level-knowledge-distillation","title":"MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models","date":"2024-07-03","arxiv_id":"2407.02775","repositories_listed":0,"syntology":null},{"url":null,"slug":"qlsc-a-query-latent-semantic-calibrator-for","title":"QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering","date":"2024-04-30","arxiv_id":"2404.19316","repositories_listed":0,"syntology":null},{"url":null,"slug":"gemquad-generating-multilingual-question","title":"GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning","date":"2024-04-14","arxiv_id":"2404.09163","repositories_listed":0,"syntology":null},{"url":null,"slug":"comprehensive-study-on-german-language-models","title":"Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding","date":"2024-04-08","arxiv_id":"2404.05694","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-small-language-models-help-large-language","title":"Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought","date":"2024-04-04","arxiv_id":"2404.03414","repositories_listed":0,"syntology":null},{"url":null,"slug":"xaiqa-explainer-based-data-augmentation-for","title":"XAIQA: Explainer-Based Data Augmentation for Extractive Question Answering","date":"2023-12-06","arxiv_id":"2312.03567","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-leveraging-llms-for-conditional-qa","title":"Towards leveraging LLMs for Conditional QA","date":"2023-12-02","arxiv_id":"2312.01143","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-pre-trained-generative-models-for","title":"Adapting Pre-trained Generative Models for Extractive Question Answering","date":"2023-11-06","arxiv_id":"2311.02961","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerated-materials-language-processing","title":"Accelerated materials language processing enabled by GPT","date":"2023-08-18","arxiv_id":"2308.09354","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-the-challenges-of-hci-an-application","title":"Mapping the Challenges of HCI: An Application and Evaluation of ChatGPT and GPT-4 for Mining Insights at Scale","date":"2023-06-08","arxiv_id":"2306.05036","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-extractive-question-answering-system","title":"Building Extractive Question Answering System to Support Human-AI Health Coaching Model for Sleep Domain","date":"2023-05-31","arxiv_id":"2305.19707","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-frustratingly-easy-improvement-for-position","title":"A Frustratingly Easy Improvement for Position Embeddings via Random Padding","date":"2023-05-08","arxiv_id":"2305.04859","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-language-gap-knowledge-injected","title":"Bridging the Language Gap: Knowledge Injected Multilingual Question Answering","date":"2023-04-06","arxiv_id":"2304.03159","repositories_listed":0,"syntology":null},{"url":null,"slug":"zerotop-zero-shot-task-oriented-semantic","title":"ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models","date":"2022-12-21","arxiv_id":"2212.10815","repositories_listed":0,"syntology":null},{"url":null,"slug":"momentum-contrastive-pre-training-for","title":"Momentum Contrastive Pre-training for Question Answering","date":"2022-12-12","arxiv_id":"2212.05762","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-to-the-right-mitigating-relative","title":"Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering","date":"2022-10-26","arxiv_id":"2210.14541","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-sample-efficient-nlp-models-more-robust","title":"Are Sample-Efficient NLP Models More Robust?","date":"2022-10-12","arxiv_id":"2210.06456","repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-question-answering-on-queries-in","title":"Extractive Question Answering on Queries in Hindi and Tamil","date":"2022-09-27","arxiv_id":"2210.06356","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-the-intent-landscape-of-real-world","title":"Building the Intent Landscape of Real-World Conversational Corpora with Extractive Question-Answering Transformers","date":"2022-08-26","arxiv_id":"2208.12886","repositories_listed":0,"syntology":null},{"url":null,"slug":"longhorns-at-dadc-2022-how-many-linguists-1","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks.","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"longhorns-at-dadc-2022-how-many-linguists","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks","date":"2022-06-29","arxiv_id":"2206.14729","repositories_listed":0,"syntology":null},{"url":"/paper/natural-questions-in-icelandic","slug":"natural-questions-in-icelandic","title":"Natural Questions in Icelandic","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stars-at-quran-qa-2022-building-automatic","title":"Stars at Qur’an QA 2022: Building Automatic Extractive Question Answering Systems for the Holy Qur’an with Transformer Models and Releasing a New Dataset","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-character-are-subwords-good-enough-1","title":"Breaking Character: Are Subwords Good Enough for MRLs After All?","date":"2022-04-10","arxiv_id":"2204.04748","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-zero-shot-event-extraction-via","title":"Improving Zero-Shot Event Extraction via Sentence Simplification","date":"2022-04-06","arxiv_id":"2204.02531","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-character-are-subwords-good-enough","title":"Breaking Character: Are Subwords Good Enough for MRLs After All?","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-self-training-of-machine-reading","title":"Cooperative Self-training of Machine Reading Comprehension","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mosaic-augmentation-for-text-cropping-and","title":"Mosaic Augmentation for Text: Cropping and Collaging as Cross-Domain Techniques","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rxwhyqa-a-clinical-question-answering-dataset","title":"Development of an Extractive Clinical Question Answering Dataset with Multi-Answer and Multi-Focus Questions","date":"2022-01-07","arxiv_id":"2201.02517","repositories_listed":0,"syntology":null},{"url":null,"slug":"models-in-the-loop-aiding-crowdworkers-with","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","date":"2021-12-16","arxiv_id":"2112.09062","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-explanations-be-useful-for-calibrating-1","title":"Can Explanations Be Useful for Calibrating Black Box Models?","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"delving-deep-into-extractive-question","title":"Delving Deep into Extractive Question Answering Data","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-multilingual-capabilities-of-very-1","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-bandit-learning-from-user-feedback","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"autoeqa-auto-encoding-questions-for","title":"AutoEQA: Auto-Encoding Questions for Extractive Question Answering","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-semi-supervised-transfer-learning","title":"Cooperative Semi-Supervised Transfer Learning of Machine Reading Comprehension","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-search-as-extractive-paraphrase-span","title":"Semantic Search as Extractive Paraphrase Span Detection","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-guided-generative-models-for","title":"Attention-guided Generative Models for Extractive Question Answering","date":"2021-10-12","arxiv_id":"2110.06393","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-transformer-based","title":"A Comparative Study of Transformer-Based Language Models on Extractive Question Answering","date":"2021-10-07","arxiv_id":"2110.03142","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-retrieval-of-tables-and-texts","title":"Multi-modal Retrieval of Tables and Texts Using Tri-encoder Models","date":"2021-08-09","arxiv_id":"2108.04049","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robustly-optimized-bert-pre-training","title":"A Robustly Optimized BERT Pre-training Approach with Post-training","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reasonbert-pre-trained-to-reason-with-distant-1","title":"ReasonBert: Pre-trained to Reason with Distant Supervision","date":"2021-05-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-retrieval-optimized-multi-task","title":"Efficient Retrieval Optimized Multi-task Learning","date":"2021-04-20","arxiv_id":"2104.10129","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-confident-machine-reading","title":"Towards Confident Machine Reading Comprehension","date":"2021-01-20","arxiv_id":"2101.07942","repositories_listed":0,"syntology":null},{"url":"/paper/efficientqa-a-roberta-based-phrase-indexed","slug":"efficientqa-a-roberta-based-phrase-indexed","title":"EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System","date":"2021-01-06","arxiv_id":"2101.02157","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-question-answering-from","title":"Multilingual Question Answering from Formatted Text applied to Conversational Agents","date":"2019-10-10","arxiv_id":"1910.04659","repositories_listed":0,"syntology":null}],"syntology_records":12,"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":12,"papers_where_code_ran_first_page":"/task/extractive-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":2,"url":"/task/extractive-question-answering/papers/2","json":"/task/extractive-question-answering/papers/2.json","rows":2},{"order":"ran","page":1,"of":1,"url":"/task/extractive-question-answering/papers/ran/1","json":"/task/extractive-question-answering/papers/ran/1.json","rows":12}],"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":"8217c21d7c88af055800685d1ae00698dc4778c9213fc880dd4843aae1ab6cb7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}