{"url":"/dataset/popqa","name":"PopQA","full_name":null,"description_markdown":"**PopQA** is an open-domain QA dataset with 14k QA pairs with fine-grained Wikidata entity ID, Wikipedia page views, and relationship type information.\r\n\r\nSource: [https://paperswithcode.com/paper/when-not-to-trust-language-models](https://arxiv.org/pdf/2212.10511v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2212.10511v1.pdf](https://arxiv.org/pdf/2212.10511v1.pdf)","description_withheld":null,"homepage":"https://github.com/alextmallen/adaptive-retrieval","introduced_date":"2022-12-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/when-not-to-trust-language-models","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","first_author":"Alex Mallen","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"},{"name":"Retrieval","url":"/task/retrieval","datasets_with_task":"/datasets/task/retrieval"},{"name":"Knowledge Probing","url":"/task/knowledge-probing","datasets_with_task":"/datasets/task/knowledge-probing"},{"name":"Memorization","url":"/task/memorization","datasets_with_task":"/datasets/task/memorization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PopQA"],"data_loaders":[],"num_papers_in_archive":91,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-popqa","task":"Question Answering","dataset_variant":"PopQA","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SelfRAG-7b","paper":"/paper/self-rag-learning-to-retrieve-generate-and","metrics":{"Accuracy":"54.9"},"code_links":[{"title":"ruc-nlpir/flashrag","url":"https://github.com/ruc-nlpir/flashrag"},{"title":"AkariAsai/self-rag","url":"https://github.com/AkariAsai/self-rag"},{"title":"fate-ubw/raglab","url":"https://github.com/fate-ubw/raglab"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"},{"title":"llm-lab-org/CLASP","url":"https://github.com/llm-lab-org/CLASP"},{"title":"kaistai/semiparametric_token-sequence_co-supervision","url":"https://github.com/kaistai/semiparametric_token-sequence_co-supervision"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/self-rag-learning-to-retrieve-generate-and","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","date":"2023-10-17","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":8,"samples_unverified":6,"pointer_only_for_licence":3,"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":1,"samples_harvested":14,"samples_ran":8,"samples_unverified":6,"pointer_only_for_licence":3,"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."}