{"url":"/task/text-generation","name":"Text Generation","slug":"text-generation","description_markdown":"**Text Generation** is the task of generating text with the goal of appearing indistinguishable to human-written text. This task is more formally known as \"natural language generation\" in the literature.\r\n\r\nText generation can be addressed with Markov processes or deep generative models like LSTMs. Recently, some of the most advanced methods for text generation include [BART](/method/bart), [GPT](/method/gpt) and other [GAN-based approaches](/method/gan). Text generation systems are evaluated either through human ratings or automatic evaluation metrics like METEOR, ROUGE, and BLEU. \r\n\r\nFurther readings:\r\n\r\n- [The survey: Text generation models in deep learning](https://www.sciencedirect.com/science/article/pii/S1319157820303360)\r\n- [Modern Methods for Text Generation](https://arxiv.org/abs/2009.04968)\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Adversarial Ranking for Language Generation](https://arxiv.org/abs/1705.11001) )</span>","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":5335,"papers_with_code":2047,"benchmarks":20,"benchmark_tables_in_archive":155,"benchmark_tables_shown":155,"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":162,"subtasks":25,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-generation-on-dart","slug":"text-generation-on-dart","dataset":"DART","dataset_url":"/dataset/dart","rows_in_archive":7,"metrics":["BLEU","METEOR","FactSpotter"],"first_row_in_archive_order":{"model":"T5B Baseline","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_url":"/paper/factspotter-evaluating-the-factual","paper_date":"2023-10-25","arxiv_id":null,"code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-coco-captions","slug":"text-generation-on-coco-captions","dataset":"COCO Captions","dataset_url":"/dataset/coco-captions","rows_in_archive":5,"metrics":["BLEU-2","BLEU-3","BLEU-4","BLEU-5"],"first_row_in_archive_order":{"model":"LeakGAN","paper_title":"Long Text Generation via Adversarial Training with Leaked Information","paper_url":"/paper/long-text-generation-via-adversarial-training","paper_date":"2017-09-24","arxiv_id":"1709.08624","code_links":[{"title":"CR-Gjx/LeakGAN","url":"https://github.com/CR-Gjx/LeakGAN"},{"title":"nurpeiis/LeakGAN-PyTorch","url":"https://github.com/nurpeiis/LeakGAN-PyTorch"},{"title":"valko073/LyricsGANs","url":"https://github.com/valko073/LyricsGANs"},{"title":"rupes438/CodeGen","url":"https://github.com/rupes438/CodeGen"},{"title":"liyzcj/leakgan-py3","url":"https://github.com/liyzcj/leakgan-py3"},{"title":"universebh/text_generation_fsa_gan","url":"https://github.com/universebh/text_generation_fsa_gan"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/text-generation-on-emnlp2017-wmt","slug":"text-generation-on-emnlp2017-wmt","dataset":"EMNLP2017 WMT","dataset_url":null,"rows_in_archive":5,"metrics":["BLEU-2","BLEU-3","BLEU-4","BLEU-5","NLLgen"],"first_row_in_archive_order":{"model":"LeakGAN","paper_title":"Long Text Generation via Adversarial Training with Leaked Information","paper_url":"/paper/long-text-generation-via-adversarial-training","paper_date":"2017-09-24","arxiv_id":"1709.08624","code_links":[{"title":"CR-Gjx/LeakGAN","url":"https://github.com/CR-Gjx/LeakGAN"},{"title":"nurpeiis/LeakGAN-PyTorch","url":"https://github.com/nurpeiis/LeakGAN-PyTorch"},{"title":"valko073/LyricsGANs","url":"https://github.com/valko073/LyricsGANs"},{"title":"rupes438/CodeGen","url":"https://github.com/rupes438/CodeGen"},{"title":"liyzcj/leakgan-py3","url":"https://github.com/liyzcj/leakgan-py3"},{"title":"universebh/text_generation_fsa_gan","url":"https://github.com/universebh/text_generation_fsa_gan"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/text-generation-on-redial","slug":"text-generation-on-redial","dataset":"ReDial","dataset_url":"/dataset/redial","rows_in_archive":5,"metrics":["Distinct-3","Distinct-4","Distinct-2","Perplexity"],"first_row_in_archive_order":{"model":"UniCRS","paper_title":"Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning","paper_url":"/paper/towards-unified-conversational-recommender","paper_date":"2022-06-19","arxiv_id":"2206.09363","code_links":[{"title":"rucaibox/unicrs","url":"https://github.com/rucaibox/unicrs"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-commongen-1","slug":"text-generation-on-commongen-1","dataset":"CommonGen","dataset_url":"/dataset/commongen","rows_in_archive":4,"metrics":["CIDEr","METEOR","BLEU-4","SPICE"],"first_row_in_archive_order":{"model":"UniLM","paper_title":"CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning","paper_url":"/paper/commongen-a-constrained-text-generation","paper_date":"2019-11-09","arxiv_id":"1911.03705","code_links":[{"title":"INK-USC/CommonGen","url":"https://github.com/INK-USC/CommonGen"},{"title":"allenai/CommonGen-Eval","url":"https://github.com/allenai/CommonGen-Eval"},{"title":"varshakr24/CommonsenseReasoning","url":"https://github.com/varshakr24/CommonsenseReasoning"}],"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/text-generation-on-rocstories","slug":"text-generation-on-rocstories","dataset":"ROCStories","dataset_url":"/dataset/rocstories","rows_in_archive":4,"metrics":["BLEU-1","Perplexity"],"first_row_in_archive_order":{"model":"Beam search + A*esque (beam)","paper_title":"NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics","paper_url":"/paper/neurologic-a-esque-decoding-constrained-text","paper_date":"2021-12-16","arxiv_id":"2112.08726","code_links":[{"title":"GXimingLu/a_star_neurologic","url":"https://github.com/GXimingLu/a_star_neurologic"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-chinese-poems","slug":"text-generation-on-chinese-poems","dataset":"Chinese Poems","dataset_url":null,"rows_in_archive":3,"metrics":["BLEU-2"],"first_row_in_archive_order":{"model":"RankGAN","paper_title":"Adversarial Ranking for Language Generation","paper_url":"/paper/adversarial-ranking-for-language-generation","paper_date":"2017-05-31","arxiv_id":"1705.11001","code_links":[{"title":"desire2020/RankGAN","url":"https://github.com/desire2020/RankGAN"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-czech-restaurant","slug":"text-generation-on-czech-restaurant","dataset":"Czech restaurant information","dataset_url":"/dataset/czech-restaurant-information","rows_in_archive":3,"metrics":["METEOR"],"first_row_in_archive_order":{"model":"TGen++","paper_title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","paper_url":"/paper/the-gem-benchmark-natural-language-generation","paper_date":"2021-02-02","arxiv_id":"2102.01672","code_links":[],"syntology":null}},{"leaderboard":"/sota/text-generation-on-openwebtext","slug":"text-generation-on-openwebtext","dataset":"OpenWebText","dataset_url":"/dataset/openwebtext","rows_in_archive":3,"metrics":["eval_loss"],"first_row_in_archive_order":{"model":"GPT2-Hermite","paper_title":"Polynomial, trigonometric, and tropical activations","paper_url":"/paper/learnable-polynomial-trigonometric-and","paper_date":"2025-02-03","arxiv_id":"2502.01247","code_links":[{"title":"K-H-Ismail/torchortho","url":"https://github.com/K-H-Ismail/torchortho"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-sciq","slug":"text-generation-on-sciq","dataset":"SciQ","dataset_url":"/dataset/sciq","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LLaMA-65B+CFG (zero-shot)","paper_title":"Stay on topic with Classifier-Free Guidance","paper_url":"/paper/stay-on-topic-with-classifier-free-guidance","paper_date":"2023-06-30","arxiv_id":"2306.17806","code_links":[],"syntology":null}},{"leaderboard":"/sota/text-generation-on-yahoo-questions","slug":"text-generation-on-yahoo-questions","dataset":"Yahoo Questions","dataset_url":null,"rows_in_archive":3,"metrics":["NLL","KL","Perplexity"],"first_row_in_archive_order":{"model":"Aggressive VAE","paper_title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders","paper_url":"/paper/lagging-inference-networks-and-posterior","paper_date":"2019-01-16","arxiv_id":"1901.05534","code_links":[{"title":"jxhe/vae-lagging-encoder","url":"https://github.com/jxhe/vae-lagging-encoder"},{"title":"spokoyny/spokoyny.github.io","url":"https://github.com/spokoyny/spokoyny.github.io"}],"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/text-generation-on-adgen","slug":"text-generation-on-adgen","dataset":"ADGEN","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU-4"],"first_row_in_archive_order":{"model":"BART (TextBox 2.0)","paper_title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","paper_url":"/paper/textbox-2-0-a-text-generation-library-with","paper_date":"2022-12-26","arxiv_id":"2212.13005","code_links":[{"title":"RUCAIBox/TextBox","url":"https://github.com/RUCAIBox/TextBox"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/text-generation-on-cmu-se","slug":"text-generation-on-cmu-se","dataset":"CMU-SE","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU-3"],"first_row_in_archive_order":{"model":"STWGAN-GP","paper_title":"Generating Text through Adversarial Training using Skip-Thought Vectors","paper_url":"/paper/generating-text-through-adversarial-training","paper_date":"2018-08-27","arxiv_id":"1808.08703","code_links":[{"title":"afrozas/skip-thought-gan","url":"https://github.com/afrozas/skip-thought-gan"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-cnn-daily-mail","slug":"text-generation-on-cnn-daily-mail","dataset":"CNN/Daily Mail","dataset_url":"/dataset/cnn-daily-mail-1","rows_in_archive":1,"metrics":["ROUGE-L"],"first_row_in_archive_order":{"model":"PALM","paper_title":"PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation","paper_url":"/paper/palm-pre-training-an-autoencoding","paper_date":"2020-04-14","arxiv_id":"2004.07159","code_links":[{"title":"alibaba/AliceMind","url":"https://github.com/alibaba/AliceMind/tree/main/PALM"},{"title":"overwindows/PALM","url":"https://github.com/overwindows/PALM"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-csl","slug":"text-generation-on-csl","dataset":"CSL","dataset_url":"/dataset/csl","rows_in_archive":1,"metrics":["ROUGE-L"],"first_row_in_archive_order":{"model":"BART (TextBox 2.0)","paper_title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","paper_url":"/paper/textbox-2-0-a-text-generation-library-with","paper_date":"2022-12-26","arxiv_id":"2212.13005","code_links":[{"title":"RUCAIBox/TextBox","url":"https://github.com/RUCAIBox/TextBox"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/text-generation-on-dailydialog","slug":"text-generation-on-dailydialog","dataset":"DailyDialog","dataset_url":"/dataset/dailydialog","rows_in_archive":1,"metrics":["BLEU-1","BLEU-2","BLEU-3","BLEU-4"],"first_row_in_archive_order":{"model":"AEM+Attention","paper_title":"An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation","paper_url":"/paper/an-auto-encoder-matching-model-for-learning","paper_date":"2018-08-27","arxiv_id":"1808.08795","code_links":[{"title":"lancopku/AMM","url":"https://github.com/lancopku/AMM"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-harmfulqa","slug":"text-generation-on-harmfulqa","dataset":"HarmfulQA","dataset_url":"/dataset/harmfulqa","rows_in_archive":1,"metrics":["ASR"],"first_row_in_archive_order":{"model":"GPT-4","paper_title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","paper_url":"/paper/red-teaming-large-language-models-using-chain","paper_date":"2023-08-18","arxiv_id":"2308.09662","code_links":[{"title":"declare-lab/red-instruct","url":"https://github.com/declare-lab/red-instruct"},{"title":"leondiao0427/seas","url":"https://github.com/leondiao0427/seas"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-lcsts","slug":"text-generation-on-lcsts","dataset":"LCSTS","dataset_url":"/dataset/lcsts","rows_in_archive":1,"metrics":["ROUGE-L"],"first_row_in_archive_order":{"model":"BART (TextBox 2.0)","paper_title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","paper_url":"/paper/textbox-2-0-a-text-generation-library-with","paper_date":"2022-12-26","arxiv_id":"2212.13005","code_links":[{"title":"RUCAIBox/TextBox","url":"https://github.com/RUCAIBox/TextBox"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/text-generation-on-ldc2016e25","slug":"text-generation-on-ldc2016e25","dataset":"LDC2016E25","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Graph2Seq","paper_title":"A Graph-to-Sequence Model for AMR-to-Text Generation","paper_url":"/paper/a-graph-to-sequence-model-for-amr-to-text","paper_date":"2018-05-07","arxiv_id":"1805.02473","code_links":[{"title":"freesunshine0316/neural-graph-to-seq-mp","url":"https://github.com/freesunshine0316/neural-graph-to-seq-mp"}],"syntology":null}},{"leaderboard":"/sota/text-generation-on-one-billion-word","slug":"text-generation-on-one-billion-word","dataset":"One Billion Word","dataset_url":"/dataset/billion-word-benchmark","rows_in_archive":1,"metrics":["JS-4"],"first_row_in_archive_order":{"model":"WGANGP + DGflow","paper_title":"Refining Deep Generative Models via Discriminator Gradient Flow","paper_url":"/paper/refining-deep-generative-models-via-1","paper_date":"2020-12-01","arxiv_id":"2012.00780","code_links":[{"title":"clear-nus/DGflow","url":"https://github.com/clear-nus/DGflow"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":null,"slug":"text-generation-on-ai2-reasoning-challenge-25","dataset":"AI2 Reasoning Challenge (25-Shot)","dataset_url":null,"rows_in_archive":0,"metrics":["normalized accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-ai2-reasoning-challenge-tr","dataset":"AI2 Reasoning Challenge TR v0.2","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-alpacaeval","dataset":"AlpacaEval","dataset_url":"/dataset/alpacaeval","rows_in_archive":0,"metrics":["win rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-alpacaeval-2-0-gpt-4-1106","dataset":"AlpacaEval 2.0 (GPT-4-1106-Preview)","dataset_url":null,"rows_in_archive":0,"metrics":["lc win rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-arabic-poetry-dataset-6th","dataset":"Arabic Poetry Dataset (6th - 21st century)","dataset_url":null,"rows_in_archive":0,"metrics":["Validation Perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-arc-challenge","dataset":"arc_challenge","dataset_url":null,"rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-arc-challenge-25-shot","dataset":"ARC Challenge (25-Shot)","dataset_url":null,"rows_in_archive":0,"metrics":["normalized accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-arc-challenge-pt","dataset":"ARC-Challenge (PT)","dataset_url":null,"rows_in_archive":0,"metrics":["normalized accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-arc-easy","dataset":"arc_easy","dataset_url":null,"rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-assin2-rte","dataset":"Assin2 RTE","dataset_url":"/dataset/assin2","rows_in_archive":0,"metrics":["f1-macro"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-assin2-sts","dataset":"Assin2 STS","dataset_url":null,"rows_in_archive":0,"metrics":["pearson"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-axb","dataset":"axb","dataset_url":null,"rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-axg","dataset":"axg","dataset_url":null,"rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-bbh-3-shot","dataset":"BBH (3-Shot)","dataset_url":null,"rows_in_archive":0,"metrics":["normalized accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-big-bench-hard-3-shot","dataset":"Big Bench Hard (3-Shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy (normalized)"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-bluex-no-images","dataset":"BLUEX (No Images)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-boolq","dataset":"BoolQ","dataset_url":"/dataset/boolq","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-calame-pt","dataset":"CALAME-PT","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-cb","dataset":"cb","dataset_url":null,"rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-censorship-0-shot","dataset":"Censorship (0-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-cola","dataset":"CoLA","dataset_url":"/dataset/cola","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-creativity-0-shot","dataset":"Creativity (0-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-crimestats","dataset":"CrimeStats","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-crows-pairs-english","dataset":"crows_pairs_english","dataset_url":null,"rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-crows-pairs-french","dataset":"crows_pairs_french","dataset_url":null,"rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-diabla","dataset":"DiaBLa","dataset_url":"/dataset/diabla","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-drop-3-shot","dataset":"Drop (3-Shot)","dataset_url":"/dataset/drop","rows_in_archive":0,"metrics":["f1 score"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-enem-challenge-no-images","dataset":"ENEM Challenge (No Images)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-faquad-nli","dataset":"FaQuAD NLI","dataset_url":null,"rows_in_archive":0,"metrics":["f1-macro"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gpqa-0-shot","dataset":"GPQA (0-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["acc_norm"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-afr","dataset":"gsarti/flores_101_afr","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-asm","dataset":"gsarti/flores_101_asm","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-cat","dataset":"gsarti/flores_101_cat","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-ceb","dataset":"gsarti/flores_101_ceb","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-ces","dataset":"gsarti/flores_101_ces","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-ckb","dataset":"gsarti/flores_101_ckb","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-cym","dataset":"gsarti/flores_101_cym","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-dan","dataset":"gsarti/flores_101_dan","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-deu","dataset":"gsarti/flores_101_deu","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-ell","dataset":"gsarti/flores_101_ell","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-eng","dataset":"gsarti/flores_101_eng","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-est","dataset":"gsarti/flores_101_est","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-fas","dataset":"gsarti/flores_101_fas","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-fin","dataset":"gsarti/flores_101_fin","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-fra","dataset":"gsarti/flores_101_fra","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-ful","dataset":"gsarti/flores_101_ful","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-glg","dataset":"gsarti/flores_101_glg","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-guj","dataset":"gsarti/flores_101_guj","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-hau","dataset":"gsarti/flores_101_hau","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-heb","dataset":"gsarti/flores_101_heb","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-mlt","dataset":"gsarti/flores_101_mlt","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-mon","dataset":"gsarti/flores_101_mon","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-msa","dataset":"gsarti/flores_101_msa","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-mya","dataset":"gsarti/flores_101_mya","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-nld","dataset":"gsarti/flores_101_nld","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-nob","dataset":"gsarti/flores_101_nob","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-npi","dataset":"gsarti/flores_101_npi","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-nso","dataset":"gsarti/flores_101_nso","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-nya","dataset":"gsarti/flores_101_nya","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-oci","dataset":"gsarti/flores_101_oci","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-orm","dataset":"gsarti/flores_101_orm","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-ory","dataset":"gsarti/flores_101_ory","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-pan","dataset":"gsarti/flores_101_pan","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-pol","dataset":"gsarti/flores_101_pol","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-por","dataset":"gsarti/flores_101_por","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-ron","dataset":"gsarti/flores_101_ron","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-rus","dataset":"gsarti/flores_101_rus","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-slk","dataset":"gsarti/flores_101_slk","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-slv","dataset":"gsarti/flores_101_slv","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-som","dataset":"gsarti/flores_101_som","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-tam","dataset":"gsarti/flores_101_tam","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-tel","dataset":"gsarti/flores_101_tel","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-tgk","dataset":"gsarti/flores_101_tgk","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-tgl","dataset":"gsarti/flores_101_tgl","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-tha","dataset":"gsarti/flores_101_tha","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-tur","dataset":"gsarti/flores_101_tur","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-ukr","dataset":"gsarti/flores_101_ukr","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-umb","dataset":"gsarti/flores_101_umb","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-urd","dataset":"gsarti/flores_101_urd","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-uzb","dataset":"gsarti/flores_101_uzb","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-vie","dataset":"gsarti/flores_101_vie","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-wol","dataset":"gsarti/flores_101_wol","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-xho","dataset":"gsarti/flores_101_xho","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-yor","dataset":"gsarti/flores_101_yor","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-zho","dataset":"gsarti/flores_101_zho_simpl","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-zho-trad","dataset":"gsarti/flores_101_zho_trad","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsarti-flores-101-zul","dataset":"gsarti/flores_101_zul","dataset_url":"/dataset/flores-101","rows_in_archive":0,"metrics":["byte_perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsm8k-5-shot","dataset":"GSM8k (5-shot)","dataset_url":"/dataset/gsm8k","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsm8k-tr","dataset":"GSM8k TR","dataset_url":"/dataset/gsm8k","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-gsm8k-tr-v0-2","dataset":"GSM8k TR v0.2","dataset_url":"/dataset/gsm8k","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-hatebr-binary","dataset":"HateBR Binary","dataset_url":null,"rows_in_archive":0,"metrics":["f1-macro"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-headqa","dataset":"HeadQA","dataset_url":"/dataset/headqa","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-hellaswag","dataset":"HellaSwag","dataset_url":"/dataset/hellaswag","rows_in_archive":0,"metrics":["Accuracy","acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-hellaswag-10-shot","dataset":"HellaSwag (10-Shot)","dataset_url":"/dataset/hellaswag","rows_in_archive":0,"metrics":["normalized accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-hellaswag-pt","dataset":"HellaSwag (PT)","dataset_url":null,"rows_in_archive":0,"metrics":["normalized accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-hellaswag-tr","dataset":"HellaSwag TR","dataset_url":"/dataset/hellaswag","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-humanness-0-shot","dataset":"Humanness (0-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-ifeval-0-shot","dataset":"IFEval (0-Shot)","dataset_url":null,"rows_in_archive":0,"metrics":["averaged accuracy","strict accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-indicglue","dataset":"IndicGLUE","dataset_url":"/dataset/indicglue","rows_in_archive":0,"metrics":["Average Accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-internet","dataset":"Internet","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-lambada-pt","dataset":"LAMBADA-PT","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-logiqa","dataset":"LogiQA","dataset_url":"/dataset/logiqa","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-math-hard-4-shot","dataset":"Math HARD (4-Shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy (exact match)"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-math-lvl-5-4-shot","dataset":"MATH Lvl 5 (4-Shot)","dataset_url":null,"rows_in_archive":0,"metrics":["exact match"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-mmlu-5-shot","dataset":"MMLU (5-Shot)","dataset_url":"/dataset/mmlu","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-mmlu-pro-5-shot","dataset":"MMLU-PRO (5-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-mmlu-tr","dataset":"MMLU TR","dataset_url":"/dataset/mmlu","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-mmlu-tr-v0-2","dataset":"MMLU TR v0.2","dataset_url":"/dataset/mmlu","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-mnli","dataset":"MNLI","dataset_url":"/dataset/multinli","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-mt-bench","dataset":"MT-Bench","dataset_url":"/dataset/mt-bench","rows_in_archive":0,"metrics":["score"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-musr-0-shot","dataset":"MuSR (0-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["acc_norm"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-nexa-scientific-tokens","dataset":"Nexa Scientific Tokens","dataset_url":null,"rows_in_archive":0,"metrics":["BLEU","Entropy Novelty","Internal Consistency"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-oab-exams","dataset":"OAB Exams","dataset_url":"/dataset/oab-exams","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-open-australian-legal-qa","dataset":"Open Australian Legal QA","dataset_url":null,"rows_in_archive":0,"metrics":["Perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-open-mindedness-0-shot","dataset":"Open-Mindedness (0-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-openbookqa","dataset":"OpenBookQA","dataset_url":"/dataset/openbookqa","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-piqa","dataset":"PIQA","dataset_url":"/dataset/piqa","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-polcontro","dataset":"PolContro","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-pt-hate-speech-binary","dataset":"PT Hate Speech Binary","dataset_url":null,"rows_in_archive":0,"metrics":["f1-macro"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-stories-jokes","dataset":"Stories/Jokes","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-talking-0-shot","dataset":"Talking (0-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-triviaqa","dataset":"TriviaQA","dataset_url":"/dataset/triviaqa","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-truthfulqa-0-shot","dataset":"TruthfulQA (0-shot)","dataset_url":"/dataset/truthfulqa","rows_in_archive":0,"metrics":["value"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-truthfulqa-pt","dataset":"TruthfulQA (PT)","dataset_url":null,"rows_in_archive":0,"metrics":["bleurt"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-truthfulqa-tr-v0-2","dataset":"TruthfulQA TR v0.2","dataset_url":"/dataset/truthfulqa","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-tweetsentbr","dataset":"tweetSentBR","dataset_url":"/dataset/tweetsentbr","rows_in_archive":0,"metrics":["f1-macro"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-unruly","dataset":"Unruly","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-w-10","dataset":"W/10","dataset_url":null,"rows_in_archive":0,"metrics":["willingness to answer"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-wic","dataset":"WiC","dataset_url":"/dataset/wic","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-wikitext-103","dataset":"WikiText-103","dataset_url":"/dataset/wikitext-103","rows_in_archive":0,"metrics":["Perplexity"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-winogrande","dataset":"WinoGrande","dataset_url":"/dataset/winogrande","rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-winogrande-5-shot","dataset":"Winogrande (5-shot)","dataset_url":"/dataset/winogrande","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-winogrande-tr","dataset":"Winogrande TR","dataset_url":"/dataset/winogrande","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-winogrande-tr-v0-2","dataset":"Winogrande TR v0.2","dataset_url":"/dataset/winogrande","rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"text-generation-on-world-knowledge-0-shot","dataset":"World Knowledge (0-shot)","dataset_url":null,"rows_in_archive":0,"metrics":["accuracy"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/glue","name":"GLUE","full_name":"General Language Understanding Evaluation benchmark","num_papers_in_archive":3197},{"url":"/dataset/mmlu","name":"MML","full_name":"Massive Multitask Language Understanding","num_papers_in_archive":1922},{"url":"/dataset/gsm8k","name":"GSM8K","full_name":"","num_papers_in_archive":1881},{"url":"/dataset/multinli","name":"MultiNLI","full_name":"Multi-Genre Natural Language Inference","num_papers_in_archive":1830},{"url":"/dataset/wikitext-2","name":"WikiText-2","full_name":"WikiText-2","num_papers_in_archive":1081},{"url":"/dataset/hellaswag","name":"HellaSwag","full_name":"","num_papers_in_archive":994},{"url":"/dataset/triviaqa","name":"TriviaQA","full_name":"","num_papers_in_archive":953},{"url":"/dataset/piqa","name":"PIQA","full_name":"Physical Interaction: Question Answering","num_papers_in_archive":772},{"url":"/dataset/cola","name":"CoLA","full_name":"Corpus of Linguistic Acceptability","num_papers_in_archive":710},{"url":"/dataset/winogrande","name":"WinoGrande","full_name":"","num_papers_in_archive":703},{"url":"/dataset/boolq","name":"BoolQ","full_name":"Boolean Questions","num_papers_in_archive":701},{"url":"/dataset/openbookqa","name":"OpenBookQA","full_name":"OBQA","num_papers_in_archive":635},{"url":"/dataset/truthfulqa","name":"TruthfulQA","full_name":"","num_papers_in_archive":607},{"url":"/dataset/wikitext-103","name":"WikiText-103","full_name":"WikiText-103","num_papers_in_archive":560},{"url":"/dataset/mt-bench","name":"MT-Bench","full_name":"","num_papers_in_archive":531},{"url":"/dataset/cnn-daily-mail-1","name":"CNN/Daily Mail","full_name":"CNN/Daily Mail","num_papers_in_archive":530},{"url":"/dataset/dailydialog","name":"DailyDialog","full_name":"","num_papers_in_archive":399},{"url":"/dataset/drop","name":"DROP","full_name":"Discrete Reasoning Over Paragraphs","num_papers_in_archive":382},{"url":"/dataset/bookcorpus","name":"BookCorpus","full_name":"","num_papers_in_archive":344},{"url":"/dataset/openwebtext","name":"OpenWebText","full_name":"","num_papers_in_archive":207},{"url":"/dataset/wic","name":"WiC","full_name":"Words in Context","num_papers_in_archive":206},{"url":"/dataset/coco-captions","name":"COCO Captions","full_name":"","num_papers_in_archive":203},{"url":"/dataset/sciq","name":"SciQ","full_name":"SciQ","num_papers_in_archive":183},{"url":"/dataset/eli5","name":"ELI5","full_name":"ELI5","num_papers_in_archive":158},{"url":"/dataset/rocstories","name":"ROCStories","full_name":"","num_papers_in_archive":152},{"url":"/dataset/billion-word-benchmark","name":"Billion Word Benchmark","full_name":"","num_papers_in_archive":141},{"url":"/dataset/alpacaeval","name":"AlpacaEval","full_name":"","num_papers_in_archive":131},{"url":"/dataset/logiqa","name":"LogiQA","full_name":"","num_papers_in_archive":127},{"url":"/dataset/writingprompts","name":"WritingPrompts","full_name":"","num_papers_in_archive":118},{"url":"/dataset/the-stack","name":"The Stack","full_name":"","num_papers_in_archive":115},{"url":"/dataset/commongen","name":"CommonGen","full_name":"","num_papers_in_archive":108},{"url":"/dataset/redial","name":"ReDial","full_name":"","num_papers_in_archive":105},{"url":"/dataset/e2e","name":"E2E","full_name":"End-to-End NLG Challenge","num_papers_in_archive":90},{"url":"/dataset/flores-101","name":"FLoRes-101","full_name":"","num_papers_in_archive":86},{"url":"/dataset/realnews","name":"RealNews","full_name":"","num_papers_in_archive":80},{"url":"/dataset/vqg","name":"VQG","full_name":"Visual Question Generation","num_papers_in_archive":80},{"url":"/dataset/sentence-compression","name":"Sentence Compression","full_name":"","num_papers_in_archive":63},{"url":"/dataset/tinystories","name":"TinyStories","full_name":"","num_papers_in_archive":62},{"url":"/dataset/lcsts","name":"LCSTS","full_name":"","num_papers_in_archive":58},{"url":"/dataset/mutual","name":"MuTual","full_name":"MuTual","num_papers_in_archive":55},{"url":"/dataset/opendialkg","name":"OpenDialKG","full_name":"","num_papers_in_archive":55},{"url":"/dataset/mtnt","name":"MTNT","full_name":"","num_papers_in_archive":52},{"url":"/dataset/dart","name":"DART","full_name":"","num_papers_in_archive":45},{"url":"/dataset/ccmatrix","name":"CCMatrix","full_name":"","num_papers_in_archive":42},{"url":"/dataset/csl","name":"CSL","full_name":"","num_papers_in_archive":34},{"url":"/dataset/image-paragraph-captioning","name":"Image Paragraph Captioning","full_name":"","num_papers_in_archive":31},{"url":"/dataset/conan","name":"CONAN","full_name":"COunter NArratives through Nichesourcing","num_papers_in_archive":27},{"url":"/dataset/kptimes","name":"KPTimes","full_name":"","num_papers_in_archive":27},{"url":"/dataset/kelm","name":"KELM","full_name":"","num_papers_in_archive":24},{"url":"/dataset/moral-stories","name":"Moral Stories","full_name":"","num_papers_in_archive":24},{"url":"/dataset/headqa","name":"HeadQA","full_name":"","num_papers_in_archive":23},{"url":"/dataset/amr-bank","name":"AMR Bank","full_name":"Abstract Meaning Representation","num_papers_in_archive":22},{"url":"/dataset/coco-cn","name":"COCO-CN","full_name":"","num_papers_in_archive":21},{"url":"/dataset/wiqa","name":"WIQA","full_name":"What-If Question Answering","num_papers_in_archive":21},{"url":"/dataset/robocup","name":"RoboCup","full_name":"RoboCup","num_papers_in_archive":20},{"url":"/dataset/indicglue","name":"IndicGLUE","full_name":"Indic General Language Understanding Evaluation Benchmark","num_papers_in_archive":16},{"url":"/dataset/celebv-text","name":"CelebV-Text","full_name":"","num_papers_in_archive":15},{"url":"/dataset/opusparcus","name":"Opusparcus","full_name":"","num_papers_in_archive":15},{"url":"/dataset/amazonqa","name":"AmazonQA","full_name":"","num_papers_in_archive":14},{"url":"/dataset/timetravel","name":"TimeTravel","full_name":"","num_papers_in_archive":14},{"url":"/dataset/personaldialog","name":"PersonalDialog","full_name":"","num_papers_in_archive":13},{"url":"/dataset/roscoe","name":"ROSCOE","full_name":"","num_papers_in_archive":13},{"url":"/dataset/opus","name":"OPUS","full_name":"open parallel corpus","num_papers_in_archive":12},{"url":"/dataset/cc-stories","name":"CC-Stories","full_name":"CC-Stories","num_papers_in_archive":10},{"url":"/dataset/chart2text","name":"Chart2Text","full_name":"Chart Summarization Dataset","num_papers_in_archive":10},{"url":"/dataset/chatharuhi-54k","name":"ChatHaruhi","full_name":"ChatHaruhi: Reviving Anime Character in Reality via Large Language Model","num_papers_in_archive":10},{"url":"/dataset/wikiatomicedits","name":"WikiAtomicEdits","full_name":"","num_papers_in_archive":10},{"url":"/dataset/harmfulqa","name":"HarmfulQA","full_name":"HarmfulQA","num_papers_in_archive":9},{"url":"/dataset/logic2text","name":"Logic2Text","full_name":null,"num_papers_in_archive":8},{"url":"/dataset/longform","name":"LongForm","full_name":"","num_papers_in_archive":8},{"url":"/dataset/wikitablet","name":"WikiTableT","full_name":"WikiTableT","num_papers_in_archive":8},{"url":"/dataset/vnhsge","name":"VNHSGE","full_name":"VietNamese High School Graduation Examination Dataset for Large Language Models","num_papers_in_archive":7},{"url":"/dataset/arxiv-10","name":"arXiv-10","full_name":"","num_papers_in_archive":6},{"url":"/dataset/cells","name":"CELLS","full_name":"","num_papers_in_archive":6},{"url":"/dataset/cluecorpus2020","name":"CLUECorpus2020","full_name":"","num_papers_in_archive":6},{"url":"/dataset/microsoft-research-social-media-conversation","name":"Microsoft Research Social Media Conversation Corpus","full_name":"","num_papers_in_archive":6},{"url":"/dataset/weblinx","name":"WebLINX","full_name":"Real-World Website Navigation with Multi-Turn","num_papers_in_archive":6},{"url":"/dataset/mlb-dataset","name":"MLB Dataset","full_name":"","num_papers_in_archive":5},{"url":"/dataset/pomo","name":"PoMo","full_name":"","num_papers_in_archive":5},{"url":"/dataset/risawoz","name":"RiSAWOZ","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/rucola","name":"RuCoLA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/spatialvoc2k","name":"SpatialVOC2K","full_name":"","num_papers_in_archive":5},{"url":"/dataset/stackex","name":"STACKEX","full_name":"STACKEX","num_papers_in_archive":5},{"url":"/dataset/taiga-corpus","name":"Taiga Corpus","full_name":"An open-source corpus for machine learning.","num_papers_in_archive":5},{"url":"/dataset/tweetsentbr","name":"tweetSentBR","full_name":"","num_papers_in_archive":5},{"url":"/dataset/diabla","name":"DiaBLa","full_name":"","num_papers_in_archive":4},{"url":"/dataset/goal","name":"Goal","full_name":"","num_papers_in_archive":4},{"url":"/dataset/wikipedia-generation","name":"Wikipedia Generation","full_name":"Wikipedia Generation","num_papers_in_archive":4},{"url":"/dataset/cannot","name":"CANNOT","full_name":"Compilation of ANnotated, Negation-Oriented Text-pairs","num_papers_in_archive":3},{"url":"/dataset/dr-bench","name":"DR.BENCH","full_name":"Diagnostic Reasoning Benchmark for clinical natural language processing","num_papers_in_archive":3},{"url":"/dataset/oab-exams","name":"OAB Exams","full_name":"","num_papers_in_archive":3},{"url":"/dataset/textbox-2-0","name":"TextBox 2.0","full_name":"","num_papers_in_archive":3},{"url":"/dataset/visual-writing-prompts","name":"Visual Writing Prompts","full_name":"","num_papers_in_archive":3},{"url":"/dataset/wikidocedits","name":"WikiDocEdits","full_name":"","num_papers_in_archive":3},{"url":"/dataset/ytd-18m","name":"YTD-18M","full_name":"","num_papers_in_archive":3},{"url":"/dataset/clse","name":"CLSE","full_name":"Corpus of Linguistically Significant Entities","num_papers_in_archive":2},{"url":"/dataset/codesyntax","name":"CodeSyntax","full_name":"","num_papers_in_archive":2},{"url":"/dataset/concise","name":"Concise","full_name":"","num_papers_in_archive":2},{"url":"/dataset/czech-restaurant-information","name":"Czech restaurant information","full_name":"","num_papers_in_archive":2},{"url":"/dataset/dialoconan","name":"DIALOCONAN","full_name":"","num_papers_in_archive":2},{"url":"/dataset/dtgb","name":"DTGB","full_name":"Dynamic Text-attributed Graph Benchmark","num_papers_in_archive":2},{"url":"/dataset/exhvv","name":"ExHVV","full_name":"","num_papers_in_archive":2},{"url":"/dataset/kaleidoscope","name":"Kaleidoscope","full_name":"Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation","num_papers_in_archive":2},{"url":"/dataset/live-comment-dataset","name":"Live Comment Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/negotiation-dialogues-dataset","name":"Negotiation Dialogues Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/qtuna","name":"QTuna","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/taodescribe","name":"TaoDescribe","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/threatgram-101-extreme-telegram-data","name":"ThreatGram 101 - Extreme Telegram Data","full_name":"ThreatGram 101 - Extreme Telegram Replies Data with Threat Levels","num_papers_in_archive":2},{"url":"/dataset/aave-sae-paired-dataset","name":"AAVE/SAE Paired Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/alpaca-data-galician","name":"Alpaca Data Galician","full_name":"Alpaca Data Galician","num_papers_in_archive":1},{"url":"/dataset/appealcase","name":"AppealCase","full_name":"","num_papers_in_archive":1},{"url":"/dataset/askparents","name":"AskParents","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/avicenna-deductive-commonsense-reasoning","name":"Avicenna: Deductive Commonsense Reasoning","full_name":"","num_papers_in_archive":1},{"url":"/dataset/collie-v1","name":"COLLIE-v1","full_name":"","num_papers_in_archive":1},{"url":"/dataset/colors","name":"Colors","full_name":"","num_papers_in_archive":1},{"url":"/dataset/diaforge-utc-r-0725","name":"diaforge-utc-r-0725","full_name":"DiaFORGE UTC: Unified Tool-Calling Conversations Dataset","num_papers_in_archive":1},{"url":"/dataset/docbank-tb","name":"DocBank-TB","full_name":"DocBank-Table","num_papers_in_archive":1},{"url":"/dataset/dpgmedia2019","name":"DpgMedia2019","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/synthetic-grade-school-math-sgsm","name":"Educational Grade School Math (EGSM)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ent-desc","name":"ENT-DESC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/expository-prose","name":"Expository Prose","full_name":"Expository-Prose-V1","num_papers_in_archive":1},{"url":"/dataset/food-com-recipes-and-interactions","name":"Food.com Recipes and Interactions","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fraud-case-verdicts","name":"Fraud_Case_Verdicts","full_name":"The \"Crime Facts\" of \"Offenses of Fraudulence\" in Judicial Yuan Verdicts Dataset","num_papers_in_archive":1},{"url":"/dataset/halvest","name":"HALvest","full_name":"","num_papers_in_archive":1},{"url":"/dataset/havoc","name":"HAVOC","full_name":"Harmful Abstractions and Violations in Open Completions Benchmark","num_papers_in_archive":1},{"url":"/dataset/hixstest","name":"HiXSTest","full_name":"Hindi XSTest","num_papers_in_archive":1},{"url":"/dataset/ice-hockey-news-dataset","name":"Ice Hockey News Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ilsp-greek-evaluation-suite","name":"ILSP Greek Evaluation Suite","full_name":"","num_papers_in_archive":1},{"url":"/dataset/image-caption-quality-dataset","name":"Image Caption Quality Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/lenta-short-sentences","name":"Lenta Short Sentences","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/lipogram-e","name":"Lipogram-e","full_name":"","num_papers_in_archive":1},{"url":"/dataset/litmind-dictionary","name":"LitMind Dictionary","full_name":"","num_papers_in_archive":1},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1},{"url":"/dataset/lmsys-usp","name":"LMSYS-USP","full_name":"","num_papers_in_archive":1},{"url":"/dataset/machine-mindset-mbti-dataset","name":"Machine_Mindset_MBTI_dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mattools","name":"MatTools","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mttn","name":"MTTN","full_name":"","num_papers_in_archive":1},{"url":"/dataset/needadvice","name":"needadvice","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/onlysports-dataset","name":"OnlySports Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/opendebateevidence","name":"OpenDebateEvidence","full_name":"","num_papers_in_archive":1},{"url":"/dataset/oqgend","name":"OQGend","full_name":"OQGend","num_papers_in_archive":1},{"url":"/dataset/oqrand","name":"OQRanD","full_name":"OQRanD","num_papers_in_archive":1},{"url":"/dataset/pentachromatic-cultural-palette-dataset","name":"Pentachromatic Cultural Palette  Dataset","full_name":"Pentachromatic Cultural Palette  Dataset","num_papers_in_archive":1},{"url":"/dataset/polynews","name":"PolyNews","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ptvd","name":"PTVD","full_name":"","num_papers_in_archive":1},{"url":"/dataset/reglamento-aeronautico-colombiano-2024","name":"Reglamento_Aeronautico_Colombiano_2024","full_name":"","num_papers_in_archive":1},{"url":"/dataset/rotowire-modified","name":"Rotowire-Modified","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/situational-instructions-database","name":"SAD-Instruct","full_name":"Situational Awareness Database for Instruct-Tuning","num_papers_in_archive":1},{"url":"/dataset/sg-nlg","name":"SG-NLG","full_name":"Schema-Guided Natural Language Generation","num_papers_in_archive":1},{"url":"/dataset/sgxstest","name":"SGXSTest","full_name":"Singapore XSTest","num_papers_in_archive":1},{"url":"/dataset/student-stories-reflections-and-coding","name":"Short Stories, Adjudicator Scores and Written Reflections","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tamil-alpaca","name":"Tamil Alpaca","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tamil-alpaca-orca","name":"Tamil Alpaca Orca","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tempwikibio","name":"TempWikiBio","full_name":"","num_papers_in_archive":1},{"url":"/dataset/texygen-platform","name":"Texygen Platform","full_name":"","num_papers_in_archive":1},{"url":"/dataset/the-mafia-dataset","name":"The Mafia Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/xinhuahallucinations","name":"UHGEvalDataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ukil-db-en","name":"UKIL-DB-EN","full_name":"","num_papers_in_archive":1},{"url":"/dataset/webbrain-raw","name":"WebBrain-Raw","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wikiweb2m","name":"WikiWeb2M","full_name":"Wikipedia Webpage 2M","num_papers_in_archive":1},{"url":"/dataset/xwikiref","name":"XWikiRef","full_name":"","num_papers_in_archive":1},{"url":"/dataset/assin2","name":"ASSIN2","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/code-documentation-generation","name":"Code Documentation Generation"},{"url":"/task/concept-to-text-generation","name":"Concept-To-Text Generation"},{"url":"/task/conditional-text-generation","name":"Conditional Text Generation"},{"url":"/task/data-to-text-generation","name":"Data-to-Text Generation"},{"url":"/task/dialogue-generation","name":"Dialogue Generation"},{"url":"/task/distractor-generation","name":"Distractor Generation"},{"url":"/task/fact-based-text-editing","name":"Fact-based Text Editing"},{"url":"/task/headline-generation","name":"Headline Generation"},{"url":"/task/hint-generation","name":"Hint Generation"},{"url":"/task/molecular-description-generation","name":"Molecular description generation"},{"url":"/task/multi-document-summarization","name":"Multi-Document Summarization"},{"url":"/task/natural-language-landmark-navigation","name":"Natural Language Landmark Navigation Instructions Generation"},{"url":"/task/news-generation","name":"News Generation"},{"url":"/task/paper-generation","name":"Paper generation"},{"url":"/task/paraphrase-generation","name":"Paraphrase Generation"},{"url":"/task/pgtask","name":"Profile Generation"},{"url":"/task/question-answer-generation","name":"Question-Answer-Generation"},{"url":"/task/rules-of-thumb-generation","name":"Rules-of-thumb Generation"},{"url":"/task/sonnet-generation","name":"Sonnet Generation"},{"url":"/task/spelling-correction","name":"Spelling Correction"},{"url":"/task/story-completion","name":"Story Completion"},{"url":"/task/story-generation","name":"Story Generation"},{"url":"/task/table-to-text-generation","name":"Table-to-Text Generation"},{"url":"/task/text-infilling","name":"Text Infilling"},{"url":"/task/text-style-transfoer","name":"Text Style Transfer"}],"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":2047,"tagged_in_all":5335,"items":[{"url":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","repositories_listed":82,"syntology":{"n":20,"n_ran":16,"n_unverified":4,"n_pointer_only":16}},{"url":"/paper/show-and-tell-a-neural-image-caption","title":"Show and Tell: A Neural Image Caption Generator","date":"2014-11-17","arxiv_id":"1411.4555","repositories_listed":74,"syntology":{"n":34,"n_ran":13,"n_unverified":21,"n_pointer_only":6}},{"url":"/paper/generating-sequences-with-recurrent-neural","title":"Generating Sequences With Recurrent Neural Networks","date":"2013-08-04","arxiv_id":"1308.0850","repositories_listed":59,"syntology":{"n":37,"n_ran":7,"n_unverified":30,"n_pointer_only":4}},{"url":"/paper/bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","repositories_listed":47,"syntology":{"n":53,"n_ran":22,"n_unverified":31,"n_pointer_only":7}},{"url":"/paper/diverse-beam-search-decoding-diverse","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","date":"2016-10-07","arxiv_id":"1610.02424","repositories_listed":25,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":14}},{"url":"/paper/seqgan-sequence-generative-adversarial-nets","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","date":"2016-09-18","arxiv_id":"1609.05473","repositories_listed":23,"syntology":{"n":21,"n_ran":10,"n_unverified":11,"n_pointer_only":13}},{"url":"/paper/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"repositories_listed":21,"syntology":null},{"url":"/paper/bertscore-evaluating-text-generation-with","title":"BERTScore: Evaluating Text Generation with BERT","date":"2019-04-21","arxiv_id":"1904.09675","repositories_listed":20,"syntology":{"n":76,"n_ran":44,"n_unverified":32,"n_pointer_only":33}},{"url":"/paper/retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","repositories_listed":18,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/prefix-tuning-optimizing-continuous-prompts","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","date":"2021-01-01","arxiv_id":"2101.00190","repositories_listed":13,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/transformers-state-of-the-art-natural","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","date":"2019-10-09","arxiv_id":"1910.03771","repositories_listed":9,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","repositories_listed":9,"syntology":null},{"url":"/paper/llamafactory-unified-efficient-fine-tuning-of","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","date":"2024-03-20","arxiv_id":"2403.13372","repositories_listed":8,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/trocr-transformer-based-optical-character","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","date":"2021-09-21","arxiv_id":"2109.10282","repositories_listed":8,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/ctrl-a-conditional-transformer-language-model-1","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","date":"2019-09-11","arxiv_id":"1909.05858","repositories_listed":8,"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/nlg-evaluation-metrics-beyond-correlation","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","date":"2023-05-15","arxiv_id":"2305.08566","repositories_listed":7,"syntology":null},{"url":"/paper/plug-and-play-language-models-a-simple","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","date":"2019-12-04","arxiv_id":"1912.02164","repositories_listed":7,"syntology":{"n":22,"n_ran":4,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/mass-masked-sequence-to-sequence-pre-training","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","date":"2019-05-07","arxiv_id":"1905.02450","repositories_listed":7,"syntology":null},{"url":"/paper/qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/structured-denoising-diffusion-models-in","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","date":"2021-07-07","arxiv_id":"2107.03006","repositories_listed":6,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/neural-text-generation-with-unlikelihood","title":"Neural Text Generation with Unlikelihood Training","date":"2019-08-12","arxiv_id":"1908.04319","repositories_listed":6,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/gltr-statistical-detection-and-visualization","title":"GLTR: Statistical Detection and Visualization of Generated Text","date":"2019-06-10","arxiv_id":"1906.04043","repositories_listed":6,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/training-language-gans-from-scratch","title":"Training language GANs from Scratch","date":"2019-05-23","arxiv_id":"1905.09922","repositories_listed":6,"syntology":null},{"url":"/paper/fairseq-a-fast-extensible-toolkit-for","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","date":"2019-04-01","arxiv_id":"1904.01038","repositories_listed":6,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":5}},{"url":"/paper/long-text-generation-via-adversarial-training","title":"Long Text Generation via Adversarial Training with Leaked Information","date":"2017-09-24","arxiv_id":"1709.08624","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/geometric-gan","title":"Geometric GAN","date":"2017-05-08","arxiv_id":"1705.02894","repositories_listed":6,"syntology":null},{"url":"/paper/a-syntactic-neural-model-for-general-purpose","title":"A Syntactic Neural Model for General-Purpose Code Generation","date":"2017-04-06","arxiv_id":"1704.01696","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/boundary-seeking-generative-adversarial","title":"Boundary-Seeking Generative Adversarial Networks","date":"2017-02-27","arxiv_id":"1702.08431","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/sequence-to-sequence-learning-as-beam-search","title":"Sequence-to-Sequence Learning as Beam-Search Optimization","date":"2016-06-09","arxiv_id":"1606.02960","repositories_listed":6,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}}],"syntology_records":24,"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":2,"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"}}