{"url":"/task/sentence-completion","name":"Sentence Completion","slug":"sentence-completion","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":91,"papers_with_code":49,"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":2,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/sentence-completion-on-hellaswag","slug":"sentence-completion-on-hellaswag","dataset":"HellaSwag","dataset_url":"/dataset/hellaswag","rows_in_archive":89,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CompassMTL 567M with Tailor","paper_title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","paper_url":"/paper/task-compass-scaling-multi-task-pre-training","paper_date":"2022-10-12","arxiv_id":"2210.06277","code_links":[{"title":"cooelf/compassmtl","url":"https://github.com/cooelf/compassmtl"}],"syntology":null}}],"datasets":[{"url":"/dataset/hellaswag","name":"HellaSwag","full_name":"","num_papers_in_archive":994},{"url":"/dataset/xp3","name":"xP3","full_name":"","num_papers_in_archive":34}],"subtasks":[{"url":"/task/hurtful-sentence-completion","name":"Hurtful Sentence Completion"}],"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":49,"tagged_in_all":91,"items":[{"url":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","repositories_listed":67,"syntology":{"n":65,"n_ran":15,"n_unverified":50,"n_pointer_only":4}},{"url":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","repositories_listed":67,"syntology":{"n":48,"n_ran":22,"n_unverified":26,"n_pointer_only":23}},{"url":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","repositories_listed":57,"syntology":{"n":58,"n_ran":26,"n_unverified":32,"n_pointer_only":4}},{"url":"/paper/mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","arxiv_id":"2312.00752","repositories_listed":35,"syntology":{"n":62,"n_ran":18,"n_unverified":44,"n_pointer_only":28}},{"url":"/paper/llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","repositories_listed":19,"syntology":{"n":52,"n_ran":31,"n_unverified":21,"n_pointer_only":16}},{"url":"/paper/deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","repositories_listed":14,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","repositories_listed":8,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":30,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/factuality-enhanced-language-models-for-open","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","date":"2022-06-09","arxiv_id":"2206.04624","repositories_listed":5,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":4}},{"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/mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","arxiv_id":"2404.15159","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/parameter-efficient-sparsity-crafting-from","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","date":"2024-01-05","arxiv_id":"2401.02731","repositories_listed":2,"syntology":null},{"url":"/paper/sheared-llama-accelerating-language-model-pre","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","date":"2023-10-10","arxiv_id":"2310.06694","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/investigating-subtler-biases-in-llms-ageism","title":"Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models","date":"2023-09-16","arxiv_id":"2309.08902","repositories_listed":2,"syntology":null},{"url":"/paper/the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","repositories_listed":2,"syntology":null},{"url":"/paper/bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-the-benefits-of-training-expert","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","date":"2023-02-07","arxiv_id":"2302.03202","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"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/using-deepspeed-and-megatron-to-train","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","date":"2022-01-28","arxiv_id":"2201.11990","repositories_listed":2,"syntology":null},{"url":"/paper/muppet-massive-multi-task-representations","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","date":"2021-01-26","arxiv_id":"2101.11038","repositories_listed":2,"syntology":null},{"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/aqua-an-adversarially-authored-question","title":"CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense","date":"2019-04-08","arxiv_id":"1904.04365","repositories_listed":2,"syntology":null},{"url":"/paper/recurrent-memory-networks-for-language","title":"Recurrent Memory Networks for Language Modeling","date":"2016-01-06","arxiv_id":"1601.01272","repositories_listed":2,"syntology":null},{"url":"/paper/katzbot-revolutionizing-academic-chatbot-for","title":"KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication","date":"2024-10-21","arxiv_id":"2410.16385","repositories_listed":1,"syntology":null},{"url":"/paper/mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.11909","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/language-model-sentence-completion-with-a","title":"Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method","date":"2024-02-09","arxiv_id":"2402.06125","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/mahanlp-a-marathi-natural-language-processing","title":"mahaNLP: A Marathi Natural Language Processing Library","date":"2023-11-05","arxiv_id":"2311.02579","repositories_listed":1,"syntology":null},{"url":"/paper/btrec-bert-based-trajectory-recommendation","title":"BTRec: BERT-Based Trajectory Recommendation for Personalized Tours","date":"2023-10-30","arxiv_id":"2310.19886","repositories_listed":1,"syntology":null}],"syntology_records":18,"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"}}