{"url":"/task/lambada","name":"LAMBADA","slug":"lambada","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":30,"papers_with_code":15,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/lambada-on-big-bench","slug":"lambada-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":2,"metrics":["Accuracy "],"first_row_in_archive_order":{"model":"Chinchilla-70B (zero-shot)","paper_title":"Training Compute-Optimal Large Language Models","paper_url":"/paper/training-compute-optimal-large-language","paper_date":"2022-03-29","arxiv_id":"2203.15556","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":4}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[{"url":"/task/reading-comprehension","name":"Reading Comprehension"}],"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":15,"of":15,"tagged_in_all":30,"items":[{"url":"/paper/megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","repositories_listed":10,"syntology":{"n":47,"n_ran":12,"n_unverified":35,"n_pointer_only":15}},{"url":"/paper/universal-transformers","title":"Universal Transformers","date":"2018-07-10","arxiv_id":"1807.03819","repositories_listed":8,"syntology":{"n":25,"n_ran":14,"n_unverified":11,"n_pointer_only":24}},{"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/the-lambada-dataset-word-prediction-requiring","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","date":"2016-06-20","arxiv_id":"1606.06031","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/residual-shuffle-exchange-networks-for-fast","title":"Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences","date":"2020-04-06","arxiv_id":"2004.04662","repositories_listed":2,"syntology":null},{"url":"/paper/explaining-and-improving-contrastive-decoding","title":"Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM","date":"2024-11-03","arxiv_id":"2411.01610","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-autoregression-fast-llms-via-self","title":"Beyond Autoregression: Fast LLMs via Self-Distillation Through Time","date":"2024-10-28","arxiv_id":"2410.21035","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":10}},{"url":"/paper/spectra-a-comprehensive-study-of-ternary","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","date":"2024-07-17","arxiv_id":"2407.12327","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-inconsistencies-of-conditionals","title":"Inconsistencies in Masked Language Models","date":"2022-12-30","arxiv_id":"2301.00068","repositories_listed":1,"syntology":null},{"url":"/paper/curriculum-learning-a-regularization-method","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","date":"2021-08-13","arxiv_id":"2108.06084","repositories_listed":1,"syntology":null},{"url":"/paper/neural-shuffle-exchange-networks-sequence-1","title":"Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/not-enough-data-deep-learning-to-the-rescue","title":"Not Enough Data? Deep Learning to the Rescue!","date":"2019-11-08","arxiv_id":"1911.03118","repositories_listed":1,"syntology":null},{"url":"/paper/neural-shuffle-exchange-networks-sequence","title":"Neural Shuffle-Exchange Networks -- Sequence Processing in O(n log n) Time","date":"2019-07-18","arxiv_id":"1907.07897","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/entity-tracking-improves-cloze-style-reading","title":"Entity Tracking Improves Cloze-style Reading Comprehension","date":"2018-10-05","arxiv_id":"1810.02891","repositories_listed":1,"syntology":null}],"syntology_records":5,"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"}}