{"url":"/dataset/webcpm","name":"WebCPM","full_name":null,"description_markdown":"**WebCPM** is a Chinese LFQA dataset. It contains 5,500 high-quality question-answer pairs, together with 14,315 supporting facts and 121,330 web search actions.\r\n\r\nSource: [WebCPM: Interactive Web Search for Chinese Long-form Question Answering](https://arxiv.org/pdf/2305.06849v1.pdf)\r\n\r\nImage Source: [WebCPM: Interactive Web Search for Chinese Long-form Question Answering](https://arxiv.org/pdf/2305.06849v1.pdf)","description_withheld":null,"homepage":"https://github.com/thunlp/WebCPM","introduced_date":"2023-05-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/webcpm-interactive-web-search-for-chinese","title":"WebCPM: Interactive Web Search for Chinese Long-form Question Answering","first_author":"Yujia Qin","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["WebCPM"],"data_loaders":[],"num_papers_in_archive":9,"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."}