{"url":"/dataset/complexwebquestions","name":"ComplexWebQuestions","full_name":"ComplexWebQuestions","description_markdown":"ComplexWebQuestions is a dataset for answering complex questions that require reasoning over multiple web snippets. It contains a large set of complex questions in natural language, and can be used in multiple ways:\r\n\r\n1. By interacting with a search engine;\r\n2. As a reading comprehension task: the authors release 12,725,989 web snippets that are relevant for the questions, and were collected during the development of their model;\r\n3. As a semantic parsing task: each question is paired with a SPARQL query that can be executed against Freebase to retrieve the answer.\r\n\r\nSource: [Allen Institute for AI](https://allenai.org/data/complexwebquestions)\r\nImage Source: [Talmor et al](https://arxiv.org/pdf/1803.06643v1.pdf)","description_withheld":null,"homepage":"https://allenai.org/data/complexwebquestions","introduced_date":"2018-03-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-web-as-a-knowledge-base-for-answering","title":"The Web as a Knowledge-base for Answering Complex Questions","first_author":"Alon Talmor","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Knowledge Graphs","url":"/task/knowledge-graphs","datasets_with_task":"/datasets/task/knowledge-graphs"},{"name":"Semantic Parsing","url":"/task/semantic-parsing","datasets_with_task":"/datasets/task/semantic-parsing"},{"name":"Knowledge Base Question Answering","url":"/task/knowledge-base-question-answering","datasets_with_task":"/datasets/task/knowledge-base-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ComplexWebQuestions"],"data_loaders":[{"repo":"https://github.com/happen2me/complex-web-questions-dataset","url":"https://huggingface.co/datasets/drt/complex_web_questions","frameworks":["tf","pytorch"]}],"num_papers_in_archive":62,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/knowledge-base-question-answering-on","task":"Knowledge Base Question Answering","dataset_variant":"ComplexWebQuestions","rows":6,"metrics":["Accuracy","F1","Hits@1","EM"],"first_row_in_archive_order":{"model":"ChatKBQA","paper":"/paper/chatkbqa-a-generate-then-retrieve-framework","metrics":{"Accuracy":"76.8","F1":"81.3","Hits@1":"86.0"},"code_links":[{"title":"lhrlab/chatkbqa","url":"https://github.com/lhrlab/chatkbqa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-complexwebquestions","task":"Question Answering","dataset_variant":"ComplexWebQuestions","rows":1,"metrics":["EM"],"first_row_in_archive_order":{"model":"TOME-2","paper":"/paper/mention-memory-incorporating-textual-1","metrics":{"EM":"47.7"},"code_links":[{"title":"google-research/language","url":"https://github.com/google-research/language/tree/master/language/mentionmemory"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":12,"samples_ran":8,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/chatkbqa-a-generate-then-retrieve-framework","title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","date":"2023-10-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":16,"samples_ran":11,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mention-memory-incorporating-textual-1","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","date":"2021-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/case-based-reasoning-for-natural-language","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","date":"2021-04-18","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/improving-multi-hop-knowledge-base-question","title":"Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals","date":"2021-01-11","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":2,"samples_harvested":28,"samples_ran":19,"samples_unverified":9,"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."}