{"url":"/dataset/simran-arora","name":"ConcurrentQA Benchmark","full_name":null,"description_markdown":"ConcurrentQA is a textual multi-hop QA benchmark to require concurrent retrieval over multiple data-distributions (i.e. Wikipedia and email data). The dataset follow the exact same schema and design as HotpotQA. The data set is downloadable here: https://github.com/facebookresearch/concurrentqa. It also contains model and result analysis code. This benchmark can also be used to study privacy when reasoning over data distributed in multiple privacy scopes --- i.e. Wikipedia in the public domain and emails in the private domain.\r\n\r\nThe following is a blog post about the benchmark: https://ai.facebook.com/blog/building-systems-to-reason-securely-over-private-data/","description_withheld":null,"homepage":"https://github.com/facebookresearch/concurrentqa","introduced_date":"2022-03-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/reasoning-over-public-and-private-data-in","title":"Reasoning over Public and Private Data in Retrieval-Based Systems","first_author":"Simran Arora","url":null},"license":{"name":"MIT","url":"https://github.com/facebookresearch/concurrentqa/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","datasets_with_task":"/datasets/task/open-domain-question-answering"},{"name":"Multi-hop Question Answering","url":"/task/multi-hop-question-answering","datasets_with_task":"/datasets/task/multi-hop-question-answering"},{"name":"Privacy Preserving","url":"/task/privacy-preserving","datasets_with_task":"/datasets/task/privacy-preserving"},{"name":"Multi-Hop Reading Comprehension","url":"/task/multi-hop-reading-comprehension","datasets_with_task":"/datasets/task/multi-hop-reading-comprehension"},{"name":"Privacy Preserving Deep Learning","url":"/task/privacy-preserving-deep-learning","datasets_with_task":"/datasets/task/privacy-preserving-deep-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ConcurrentQA","ConcurrentQA Benchmark"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-hop-question-answering-on-concurrentqa","task":"Multi-hop Question Answering","dataset_variant":"ConcurrentQA","rows":1,"metrics":["Answer F1"],"first_row_in_archive_order":{"model":"Multi-hop Dense Passage Retriever (MDR)","paper":"/paper/reasoning-over-public-and-private-data-in","metrics":{"Answer F1":"56.5"},"code_links":[{"title":"facebookresearch/concurrentqa","url":"https://github.com/facebookresearch/concurrentqa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/reasoning-over-public-and-private-data-in","title":"Reasoning over Public and Private Data in Retrieval-Based Systems","date":"2022-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}