{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/hellaswag","name":"HellaSwag","full_name":null,"description_markdown":"HellaSwag is a challenge dataset for evaluating commonsense NLI that is specially hard for state-of-the-art models, though its questions are trivial for humans (>95% accuracy).","description_withheld":null,"homepage":"https://rowanzellers.com/hellaswag/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/hellaswag-can-a-machine-really-finish-your","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","first_author":"Rowan Zellers","url":null},"license":{"name":"MIT","url":"https://github.com/rowanz/hellaswag/blob/master/LICENSE"},"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"parameter-efficient fine-tuning","url":"/task/parameter-efficient-fine-tuning","datasets_with_task":"/datasets/task/parameter-efficient-fine-tuning"},{"name":"Sentence Completion","url":"/task/sentence-completion","datasets_with_task":"/datasets/task/sentence-completion"}],"languages":[],"variants":["HellaSwag","HellaSwag (10-Shot)","HellaSwag TR"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/weblab-GENIAC/jhellaswag","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hellaswag","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Rowan/hellaswag","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/swap-uniba/hellaswag_ita","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ycsong-eugene/syc-hellaswag2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/malhajar/hellaswag-turkish","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/malhajar/hellaswag-tr","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/hellaswag","frameworks":["tf","jax"]}],"num_papers_in_archive":994,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentence-completion-on-hellaswag","task":"Sentence Completion","dataset_variant":"HellaSwag","rows":89,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CompassMTL 567M with Tailor","paper":"/paper/task-compass-scaling-multi-task-pre-training","metrics":{"Accuracy":"96.1"},"code_links":[{"title":"cooelf/compassmtl","url":"https://github.com/cooelf/compassmtl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-hellaswag","task":"parameter-efficient fine-tuning","dataset_variant":"HellaSwag","rows":3,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"LLaMA2-7b","paper":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","metrics":{"Accuracy (% )":"76.68"},"code_links":[{"title":"On-Point-RND/GIFT_SW","url":"https://github.com/On-Point-RND/GIFT_SW"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-hellaswag","task":"Question Answering","dataset_variant":"HellaSwag","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Shakti-LLM (2.5B)","paper":"/paper/shakti-a-2-5-billion-parameter-small-language","metrics":{"Accuracy":"52.4"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-hellaswag","task":"Text Generation","dataset_variant":"HellaSwag","rows":0,"metrics":["Accuracy","acc"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-hellaswag-10-shot","task":"Text Generation","dataset_variant":"HellaSwag (10-Shot)","rows":0,"metrics":["normalized accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-hellaswag-tr","task":"Text Generation","dataset_variant":"HellaSwag TR","rows":0,"metrics":["accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":39,"of":39,"counts":{"papers_with_a_benchmark_row":39,"with_a_code_link":32,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":39,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","slug":"gift-sw-gaussian-noise-injected-fine-tuning","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","date":"2024-08-27","arxiv_id":"2408.15300","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["On-Point-RND/GIFT_SW"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gift-sw-gaussian-noise-injected-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2408.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15300"}}}},{"paper":"/paper/mixture-of-subspaces-in-low-rank-adaptation","slug":"mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.11909","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["wutaiqiang/moslora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixture-of-subspaces-in-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2406.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11909"}}}},{"paper":"/paper/mixlora-enhancing-large-language-models-fine","slug":"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","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}}}},{"paper":"/paper/dora-weight-decomposed-low-rank-adaptation","slug":"dora-weight-decomposed-low-rank-adaptation","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","date":"2024-02-14","arxiv_id":"2402.09353","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":8,"samples_unverified":7,"pointer_only_for_licence":14,"official":{"repos":["NVlabs/DoRA","nbasyl/DoRA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dora-weight-decomposed-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2402.09353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09353"}}}},{"paper":"/paper/parameter-efficient-sparsity-crafting-from","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/llm-in-a-flash-efficient-large-language-model","slug":"llm-in-a-flash-efficient-large-language-model","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","date":"2023-12-12","arxiv_id":"2312.11514","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mamba-linear-time-sequence-modeling-with","slug":"mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","arxiv_id":"2312.00752","rows_on_this_dataset":2,"code_links":35,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":62,"samples_ran":28,"samples_constructed":7,"samples_ran_checked":20,"samples_ran_instrument_failed":8,"samples_unverified":34,"pointer_only_for_licence":29,"official":{"repos":["state-spaces/mamba","radarFudan/mamba"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mamba-linear-time-sequence-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2312.00752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00752"}}}},{"paper":"/paper/the-falcon-series-of-open-language-models","slug":"the-falcon-series-of-open-language-models","title":"The Falcon Series of Open Language Models","date":"2023-11-28","arxiv_id":"2311.16867","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"paper":"/paper/sheared-llama-accelerating-language-model-pre","slug":"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","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["princeton-nlp/llm-shearing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sheared-llama-accelerating-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2310.06694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06694"}}}},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"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","rows_on_this_dataset":4,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":52,"samples_ran":33,"samples_constructed":7,"samples_ran_checked":20,"samples_ran_instrument_failed":13,"samples_unverified":19,"pointer_only_for_licence":20,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"paper":"/paper/stay-on-topic-with-classifier-free-guidance","slug":"stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","arxiv_id":"2306.17806","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/the-cot-collection-improving-zero-shot-and","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":4,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/exploring-the-benefits-of-training-expert","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["joeljang/elm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}}}},{"paper":"/paper/two-is-better-than-many-binary-classification","slug":"two-is-better-than-many-binary-classification","title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","date":"2022-10-29","arxiv_id":"2210.16495","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["declare-lab/team"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/two-is-better-than-many-binary-classification#ran","syntology_url":"https://syntology.ai/paper/2210.16495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16495"}}}},{"paper":"/paper/knowledge-in-context-towards-knowledgeable","slug":"knowledge-in-context-towards-knowledgeable","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","date":"2022-10-28","arxiv_id":"2210.16433","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/discosense-commonsense-reasoning-with","slug":"discosense-commonsense-reasoning-with","title":"DiscoSense: Commonsense Reasoning with Discourse Connectives","date":"2022-10-22","arxiv_id":"2210.12478","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/task-compass-scaling-multi-task-pre-training","slug":"task-compass-scaling-multi-task-pre-training","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","date":"2022-10-12","arxiv_id":"2210.06277","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","rows_on_this_dataset":3,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":32,"samples_constructed":16,"samples_ran_checked":24,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"paper":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":8,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}}}},{"paper":"/paper/efficient-language-modeling-with-sparse-all","slug":"efficient-language-modeling-with-sparse-all","title":"Efficient Language Modeling with Sparse all-MLP","date":"2022-03-14","arxiv_id":"2203.06850","rows_on_this_dataset":5,"code_links":0,"syntology":null},{"paper":"/paper/using-deepspeed-and-megatron-to-train","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","rows_on_this_dataset":1,"code_links":74,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":84,"samples_ran":51,"samples_constructed":19,"samples_ran_checked":43,"samples_ran_instrument_failed":8,"samples_unverified":33,"pointer_only_for_licence":30,"official":{"repos":["microsoft/LoRA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lora-low-rank-adaptation-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2106.09685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09685"}}}},{"paper":"/paper/unicorn-on-rainbow-a-universal-commonsense","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["allenai/rainbow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unicorn-on-rainbow-a-universal-commonsense#ran","syntology_url":"https://syntology.ai/paper/2103.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13009"}}}},{"paper":"/paper/muppet-massive-multi-task-representations","slug":"muppet-massive-multi-task-representations","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","date":"2021-01-26","arxiv_id":"2101.11038","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":3,"official":{"repos":["microsoft/DeBERTa"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":3,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/towards-generalizable-neuro-symbolic-systems","slug":"towards-generalizable-neuro-symbolic-systems","title":"Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering","date":"2019-10-30","arxiv_id":"1910.14087","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/hellaswag-can-a-machine-really-finish-your","slug":"hellaswag-can-a-machine-really-finish-your","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","date":"2019-05-19","arxiv_id":"1905.07830","rows_on_this_dataset":9,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","slug":"gift-sw-gaussian-noise-injected-fine-tuning","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","date":"2024-08-27","arxiv_id":"2408.15300","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["On-Point-RND/GIFT_SW"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gift-sw-gaussian-noise-injected-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2408.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15300"}}}},{"paper":"/paper/mixture-of-subspaces-in-low-rank-adaptation","slug":"mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.11909","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["wutaiqiang/moslora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixture-of-subspaces-in-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2406.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11909"}}}},{"paper":"/paper/mixlora-enhancing-large-language-models-fine","slug":"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","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}}}},{"paper":"/paper/dora-weight-decomposed-low-rank-adaptation","slug":"dora-weight-decomposed-low-rank-adaptation","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","date":"2024-02-14","arxiv_id":"2402.09353","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":8,"samples_unverified":7,"pointer_only_for_licence":14,"official":{"repos":["NVlabs/DoRA","nbasyl/DoRA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dora-weight-decomposed-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2402.09353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09353"}}}},{"paper":"/paper/parameter-efficient-sparsity-crafting-from","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/llm-in-a-flash-efficient-large-language-model","slug":"llm-in-a-flash-efficient-large-language-model","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","date":"2023-12-12","arxiv_id":"2312.11514","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mamba-linear-time-sequence-modeling-with","slug":"mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","arxiv_id":"2312.00752","rows_on_this_dataset":2,"code_links":35,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":62,"samples_ran":28,"samples_constructed":7,"samples_ran_checked":20,"samples_ran_instrument_failed":8,"samples_unverified":34,"pointer_only_for_licence":29,"official":{"repos":["state-spaces/mamba","radarFudan/mamba"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mamba-linear-time-sequence-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2312.00752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00752"}}}},{"paper":"/paper/the-falcon-series-of-open-language-models","slug":"the-falcon-series-of-open-language-models","title":"The Falcon Series of Open Language Models","date":"2023-11-28","arxiv_id":"2311.16867","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"paper":"/paper/sheared-llama-accelerating-language-model-pre","slug":"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","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["princeton-nlp/llm-shearing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sheared-llama-accelerating-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2310.06694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06694"}}}},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"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","rows_on_this_dataset":4,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":52,"samples_ran":33,"samples_constructed":7,"samples_ran_checked":20,"samples_ran_instrument_failed":13,"samples_unverified":19,"pointer_only_for_licence":20,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"paper":"/paper/stay-on-topic-with-classifier-free-guidance","slug":"stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","arxiv_id":"2306.17806","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/the-cot-collection-improving-zero-shot-and","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":4,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/exploring-the-benefits-of-training-expert","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["joeljang/elm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}}}},{"paper":"/paper/two-is-better-than-many-binary-classification","slug":"two-is-better-than-many-binary-classification","title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","date":"2022-10-29","arxiv_id":"2210.16495","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["declare-lab/team"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/two-is-better-than-many-binary-classification#ran","syntology_url":"https://syntology.ai/paper/2210.16495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16495"}}}},{"paper":"/paper/knowledge-in-context-towards-knowledgeable","slug":"knowledge-in-context-towards-knowledgeable","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","date":"2022-10-28","arxiv_id":"2210.16433","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/discosense-commonsense-reasoning-with","slug":"discosense-commonsense-reasoning-with","title":"DiscoSense: Commonsense Reasoning with Discourse Connectives","date":"2022-10-22","arxiv_id":"2210.12478","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/task-compass-scaling-multi-task-pre-training","slug":"task-compass-scaling-multi-task-pre-training","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","date":"2022-10-12","arxiv_id":"2210.06277","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","rows_on_this_dataset":3,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":32,"samples_constructed":16,"samples_ran_checked":24,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"paper":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":8,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}}}},{"paper":"/paper/efficient-language-modeling-with-sparse-all","slug":"efficient-language-modeling-with-sparse-all","title":"Efficient Language Modeling with Sparse all-MLP","date":"2022-03-14","arxiv_id":"2203.06850","rows_on_this_dataset":5,"code_links":0,"syntology":null},{"paper":"/paper/using-deepspeed-and-megatron-to-train","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","rows_on_this_dataset":1,"code_links":74,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":84,"samples_ran":51,"samples_constructed":19,"samples_ran_checked":43,"samples_ran_instrument_failed":8,"samples_unverified":33,"pointer_only_for_licence":30,"official":{"repos":["microsoft/LoRA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lora-low-rank-adaptation-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2106.09685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09685"}}}},{"paper":"/paper/unicorn-on-rainbow-a-universal-commonsense","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["allenai/rainbow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unicorn-on-rainbow-a-universal-commonsense#ran","syntology_url":"https://syntology.ai/paper/2103.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13009"}}}},{"paper":"/paper/muppet-massive-multi-task-representations","slug":"muppet-massive-multi-task-representations","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","date":"2021-01-26","arxiv_id":"2101.11038","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":3,"official":{"repos":["microsoft/DeBERTa"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":3,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/towards-generalizable-neuro-symbolic-systems","slug":"towards-generalizable-neuro-symbolic-systems","title":"Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering","date":"2019-10-30","arxiv_id":"1910.14087","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/hellaswag-can-a-machine-really-finish-your","slug":"hellaswag-can-a-machine-really-finish-your","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","date":"2019-05-19","arxiv_id":"1905.07830","rows_on_this_dataset":9,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}}],"papers_where_code_ran":20,"papers_where_code_ran_first_page":"/dataset/hellaswag/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/hellaswag/papers/ran/1","json":"/dataset/hellaswag/papers/ran/1.json","rows":20}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":21,"samples_harvested":508,"samples_ran":328,"samples_constructed":72,"samples_ran_checked":244,"samples_ran_instrument_failed":84,"samples_unverified":180,"pointer_only_for_licence":156,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":20,"papers_with_a_run_with_no_instrument_failure":18,"papers_where_every_run_was_an_instrument_failure":2,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":35,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/sentence-completion-on-hellaswag","since_archive":"/sota/sentence-completion-on-hellaswag#since-judged","papers_judged":29,"placed":0},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-hellaswag","since_archive":"/sota/parameter-efficient-fine-tuning-on-hellaswag#since-judged","papers_judged":10,"placed":0},{"leaderboard":"/sota/question-answering-on-hellaswag","since_archive":"/sota/question-answering-on-hellaswag#since-judged","papers_judged":3,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"dc51e79664cdecb2e1de99790c749a253d35265accf69ded149c114ff0f8a4b0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}