{"url":"/dataset/commongen","name":"CommonGen","full_name":null,"description_markdown":"CommonGen is constructed through a combination of crowdsourced and existing caption corpora, consists of 79k commonsense descriptions over 35k unique concept-sets. \r\n\r\nSource: [CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning](/paper/commongen-a-constrained-text-generation)","description_withheld":null,"homepage":"https://inklab.usc.edu/CommonGen/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/commongen-a-constrained-text-generation","title":"CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning","first_author":"Bill Yuchen Lin","url":null},"license":{"name":"Custom","url":"https://inklab.usc.edu/CommonGen/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"}],"languages":[],"variants":["CommonGen"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/common_gen","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/common_gen","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":108,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-generation-on-commongen-1","task":"Text Generation","dataset_variant":"CommonGen","rows":4,"metrics":["CIDEr","METEOR","BLEU-4","SPICE"],"first_row_in_archive_order":{"model":"UniLM","paper":"/paper/commongen-a-constrained-text-generation","metrics":{"CIDEr":"14.92"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/textbox-2-0-a-text-generation-library-with","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","date":"2022-12-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-gem-benchmark-natural-language-generation","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","date":"2021-02-02","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/commongen-a-constrained-text-generation","title":"CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning","date":"2019-11-09","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}