{"url":"/dataset/romqa","name":"RoMQA","full_name":null,"description_markdown":"**RoMQA** is a benchmark for robust, multi-evidence, and multi-answer question answering (QA). RoMQA contains clusters of questions that are derived from related constraints mined from the Wikidata knowledge graph. The dataset evaluates robustness of QA models to varying constraints by measuring worst-case performance within each question cluster.\r\n\r\nSource: [RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering](https://arxiv.org/pdf/2210.14353v2.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.14353v2.pdf](https://arxiv.org/pdf/2210.14353v2.pdf)","description_withheld":null,"homepage":"https://github.com/facebookresearch/romqa","introduced_date":"2022-10-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/romqa-a-benchmark-for-robust-multi-evidence","title":"RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering","first_author":"Victor Zhong","url":null},"license":{"name":"Creative Commons Attribution-NonCommercial 4.0 International License","url":"https://github.com/facebookresearch/romqa/blob/main/LICENSE.md"},"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"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RoMQA"],"data_loaders":[],"num_papers_in_archive":2,"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":"2026-09-25T09:33:49+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."}