{"url":"/task/winogrande","name":"Winogrande","slug":"winogrande","description_markdown":null,"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":26,"papers_with_code":12,"benchmarks":0,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":null,"slug":"winogrande-on-winogrande","dataset":"WinoGrande","dataset_url":"/dataset/winogrande","rows_in_archive":0,"metrics":["Accuracy"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/winogrande","name":"WinoGrande","full_name":"","num_papers_in_archive":703}],"subtasks":[],"parent_tasks":[{"url":"/task/common-sense-reasoning","name":"Common Sense Reasoning"}],"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":12,"of":12,"tagged_in_all":26,"items":[{"url":"/paper/winogrande-an-adversarial-winograd-schema","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","date":"2019-07-24","arxiv_id":"1907.10641","repositories_listed":10,"syntology":null},{"url":"/paper/designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/bridging-the-gap-enhancing-llm-performance","title":"Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments","date":"2024-12-16","arxiv_id":"2412.12417","repositories_listed":1,"syntology":null},{"url":"/paper/texttt-metabench-a-sparse-benchmark-to","title":"$\\texttt{metabench}$ -- A Sparse Benchmark to Measure General Ability in Large Language Models","date":"2024-07-04","arxiv_id":"2407.12844","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/layer-skip-enabling-early-exit-inference-and","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","date":"2024-04-25","arxiv_id":"2404.16710","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/lisa-layerwise-importance-sampling-for-memory","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","date":"2024-03-26","arxiv_id":"2403.17919","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/are-hard-examples-also-harder-to-explain-a","title":"Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations","date":"2022-11-14","arxiv_id":"2211.07517","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/on-curriculum-learning-for-commonsense","title":"On Curriculum Learning for Commonsense Reasoning","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-out-of-domain-transfer-learning-of","title":"Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup","date":"2021-12-12","arxiv_id":"2112.06204","repositories_listed":1,"syntology":null},{"url":"/paper/unicorn-on-rainbow-a-universal-commonsense","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","date":"2021-03-24","arxiv_id":"2103.13009","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/g-daug-generative-data-augmentation-for","title":"Generative Data Augmentation for Commonsense Reasoning","date":"2020-04-24","arxiv_id":"2004.11546","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}],"syntology_records":7,"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"}}