{"url":"/dataset/researchy-questions","name":"Researchy Questions","full_name":null,"description_markdown":"Researchy Questions is a set of about 100k Bing queries that users spent the most effort on. After a labor-intensive filtering funnel from billions of queries, these \"needles in the haystack\" are non-factoid, multi-perspective questions that require a lot of sub-questions and research to answer adequately. These questions are shown to be harder than other open domain QA datasets like Natural Questions.","description_withheld":null,"homepage":"https://huggingface.co/datasets/corbyrosset/researchy_questions","introduced_date":"2024-02-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/researchy-questions-a-dataset-of-multi","title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","first_author":"Corby Rosset","url":null},"license":{"name":"cdla-permissive-2.0","url":"https://spdx.org/licenses/CDLA-Permissive-2.0"},"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[],"variants":["Researchy Questions"],"data_loaders":[],"num_papers_in_archive":3,"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."}