{"url":"/dataset/lccc","name":"LCCC","full_name":"Large-scale Cleaned Chinese Conversation corpus","description_markdown":"Contains a base version (6.8million dialogues) and a large version (12.0 million dialogues). \r\n\r\nSource: [A Large-Scale Chinese Short-Text Conversation Dataset](/paper/a-large-scale-chinese-short-text-conversation)","description_withheld":null,"homepage":"https://github.com/thu-coai/CDial-GPT","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-large-scale-chinese-short-text-conversation","title":"A Large-Scale Chinese Short-Text Conversation Dataset","first_author":"Yida Wang","url":null},"license":null,"modalities":[],"tasks":[{"name":"Dialogue Generation","url":"/task/dialogue-generation","datasets_with_task":"/datasets/task/dialogue-generation"},{"name":"Short-Text Conversation","url":"/task/short-text-conversation","datasets_with_task":"/datasets/task/short-text-conversation"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["LCCC"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/thu-coai/lccc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lccc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/thu-coai/CDial-GPT","url":"https://github.com/thu-coai/CDial-GPT","frameworks":["pytorch"]}],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}