{"url":"/task/evidence-selection","name":"Evidence Selection","slug":"evidence-selection","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":22,"papers_with_code":11,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/qasper","name":"QASPER","full_name":"","num_papers_in_archive":102}],"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":11,"of":11,"tagged_in_all":22,"items":[{"url":"/paper/chain-of-discussion-a-multi-model-framework","title":"Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering","date":"2024-02-26","arxiv_id":"2402.16313","repositories_listed":2,"syntology":null},{"url":"/paper/evidence-based-verification-for-real-world","title":"AmbiFC: Fact-Checking Ambiguous Claims with Evidence","date":"2021-04-01","arxiv_id":"2104.00640","repositories_listed":2,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/benchmarking-retrieval-augmented-multimomal","title":"Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering","date":"2025-05-22","arxiv_id":"2505.16470","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/halu-j-critique-based-hallucination-judge","title":"Halu-J: Critique-Based Hallucination Judge","date":"2024-07-17","arxiv_id":"2407.12943","repositories_listed":1,"syntology":null},{"url":"/paper/are-large-language-models-really-good-logical","title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","date":"2023-06-16","arxiv_id":"2306.09841","repositories_listed":1,"syntology":null},{"url":"/paper/slidevqa-a-dataset-for-document-visual","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","date":"2023-01-12","arxiv_id":"2301.04883","repositories_listed":1,"syntology":null},{"url":"/paper/capturing-global-structural-information-in","title":"Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network","date":"2022-10-11","arxiv_id":"2210.05499","repositories_listed":1,"syntology":null},{"url":"/paper/evidence-selection-as-a-token-level","title":"Evidence Selection as a Token-Level Prediction Task","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-of-information-seeking-questions","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","date":"2021-05-07","arxiv_id":"2105.03011","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/unsupervised-alignment-based-iterative","title":"Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering","date":"2020-05-04","arxiv_id":"2005.01218","repositories_listed":1,"syntology":null},{"url":"/paper/melu-meta-learned-user-preference-estimator","title":"MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation","date":"2019-07-31","arxiv_id":"1908.00413","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}