{"url":"/task/logical-reasoning-question-ansering","name":"Logical Reasoning Question Answering","slug":"logical-reasoning-question-ansering","description_markdown":"Introduced by ReClor (ICLR 2020), logical reasoning is to evaluate the logical reasoning ability of models for question answering.","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":3,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/logical-reasoning-question-ansering-on-reclor","slug":"logical-reasoning-question-ansering-on-reclor","dataset":"ReClor","dataset_url":"/dataset/reclor","rows_in_archive":3,"metrics":["Accuracy","Accuracy (easy)","Accuracy (hard)"],"first_row_in_archive_order":{"model":"XLNet-large","paper_title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","paper_url":"/paper/reclor-a-reading-comprehension-dataset-1","paper_date":"2020-02-11","arxiv_id":"2002.04326","code_links":[{"title":"yuweihao/reclor","url":"https://github.com/yuweihao/reclor"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}}}],"datasets":[{"url":"/dataset/reclor","name":"ReClor","full_name":"","num_papers_in_archive":88},{"url":"/dataset/trafficqa","name":"SUTD-TrafficQA","full_name":"","num_papers_in_archive":19},{"url":"/dataset/justlogic","name":"JustLogic","full_name":"","num_papers_in_archive":1},{"url":"/dataset/roomspace","name":"RoomSpace","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"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":3,"of":3,"tagged_in_all":4,"items":[{"url":"/paper/reframing-spatial-reasoning-evaluation-in","title":"Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning","date":"2024-05-23","arxiv_id":"2405.15064","repositories_listed":2,"syntology":null},{"url":"/paper/russiansuperglue-a-russian-language","title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","date":"2020-10-29","arxiv_id":"2010.15925","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/reclor-a-reading-comprehension-dataset-1","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","date":"2020-02-11","arxiv_id":"2002.04326","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}}],"syntology_records":2,"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":"2026-09-25T09:33:49+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"}}