{"url":"/task/hellaswag","name":"HellaSwag","slug":"hellaswag","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":"derived"},"counts":{"papers_tagged":39,"papers_with_code":21,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"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":21,"of":21,"tagged_in_all":39,"items":[{"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/training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/hellaswag-can-a-machine-really-finish-your","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","date":"2019-05-19","arxiv_id":"1905.07830","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":4}},{"url":"/paper/simulating-training-data-leakage-in-multiple","title":"Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation","date":"2025-05-30","arxiv_id":"2505.24263","repositories_listed":1,"syntology":null},{"url":"/paper/datadecide-how-to-predict-best-pretraining","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","date":"2025-04-15","arxiv_id":"2504.11393","repositories_listed":1,"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/what-the-hellaswag-on-the-validity-of-common","title":"What the HellaSwag? On the Validity of Common-Sense Reasoning Benchmarks","date":"2025-04-10","arxiv_id":"2504.07825","repositories_listed":1,"syntology":null},{"url":"/paper/finerweb-10bt-refining-web-data-with-llm","title":"FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering","date":"2025-01-13","arxiv_id":"2501.07314","repositories_listed":1,"syntology":null},{"url":"/paper/lora-done-rite-robust-invariant","title":"LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization","date":"2024-10-27","arxiv_id":"2410.20625","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/you-can-remove-gpt2-s-layernorm-by-fine","title":"You can remove GPT2's LayerNorm by fine-tuning","date":"2024-09-06","arxiv_id":"2409.13710","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/sage-evaluating-moral-consistency-in-large","title":"SaGE: Evaluating Moral Consistency in Large Language Models","date":"2024-02-21","arxiv_id":"2402.13709","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/attacks-on-node-attributes-in-graph-neural","title":"Attacks on Node Attributes in Graph Neural Networks","date":"2024-02-19","arxiv_id":"2402.12426","repositories_listed":1,"syntology":null},{"url":"/paper/gemini-in-reasoning-unveiling-commonsense-in","title":"Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models","date":"2023-12-29","arxiv_id":"2312.17661","repositories_listed":1,"syntology":null},{"url":"/paper/an-open-source-data-contamination-report-for","title":"An Open Source Data Contamination Report for Large Language Models","date":"2023-10-26","arxiv_id":"2310.17589","repositories_listed":1,"syntology":null},{"url":"/paper/in-contextual-bias-suppression-for-large","title":"In-Contextual Gender Bias Suppression for Large Language Models","date":"2023-09-13","arxiv_id":"2309.07251","repositories_listed":1,"syntology":null},{"url":"/paper/toward-adversarial-training-on-contextualized","title":"Toward Adversarial Training on Contextualized Language Representation","date":"2023-05-08","arxiv_id":"2305.04557","repositories_listed":1,"syntology":null},{"url":"/paper/grada-graph-generative-data-augmentation-for","title":"GraDA: Graph Generative Data Augmentation for Commonsense Reasoning","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/when-chosen-wisely-more-data-is-what-you-need-1","title":"When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation","date":"2022-03-17","arxiv_id":"2203.09391","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}}],"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"}}