{"url":"/dataset/graphquestions","name":"GraphQuestions","full_name":null,"description_markdown":"GraphQuestions is a characteristic-rich dataset designed for factoid question answering. The dataset aims to provide a systematic way of constructing QA datasets with rich and explicitly specified question characteristics. Here are some key details about GraphQuestions:\r\n\r\n1. GraphQuestions consists of a set of 5,166 factoid questions.\r\n\r\n2. Each question is associated with logical forms and ground-truth answers.\r\n\r\n3. The dataset is constructed based on Freebase, a large-scale knowledge base.\r\n\r\n4. An array of question characteristics is formalized for each question.","description_withheld":null,"homepage":"https://github.com/sunlab-osu/GraphQuestions","introduced_date":"2016-11-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/on-generating-characteristic-rich-question","title":"On Generating Characteristic-rich Question Sets for QA Evaluation","first_author":"Yu Su","url":null},"license":null,"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Semantic Parsing","url":"/task/semantic-parsing","datasets_with_task":"/datasets/task/semantic-parsing"}],"languages":[],"variants":["GraphQuestions"],"data_loaders":[],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-graphquestions","task":"Question Answering","dataset_variant":"GraphQuestions","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ChatGPT","paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","metrics":{"Accuracy":"53.1"},"code_links":[{"title":"tan92hl/complex-question-answering-evaluation-of-gpt-family","url":"https://github.com/tan92hl/complex-question-answering-evaluation-of-gpt-family"},{"title":"tan92hl/complex-question-answering-evaluation-of-chatgpt","url":"https://github.com/tan92hl/complex-question-answering-evaluation-of-chatgpt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-parsing-on-graphquestions","task":"Semantic Parsing","dataset_variant":"GraphQuestions","rows":1,"metrics":["F1 Score"],"first_row_in_archive_order":{"model":"ReasonBERTR","paper":"/paper/reasonbert-pre-trained-to-reason-with-distant","metrics":{"F1 Score":"41.3"},"code_links":[{"title":"sunlab-osu/reasonbert","url":"https://github.com/sunlab-osu/reasonbert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/reasonbert-pre-trained-to-reason-with-distant","title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","date":"2021-09-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":3,"samples_unverified":8,"pointer_only_for_licence":0,"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":11,"samples_ran":3,"samples_unverified":8,"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."}