{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":44,"tagged_in_all":102,"items":[{"url":"/paper/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_unverified":7,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":3}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","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":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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","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","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":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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","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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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","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","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_unverified":1,"n_pointer_only":4}},{"url":"/paper/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_unverified":1,"n_pointer_only":3}},{"url":"/paper/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","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","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","title":"Science Checker: Extractive-Boolean Question Answering For Scientific Fact Checking","date":"2022-04-26","arxiv_id":"2204.12263","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}