{"url":"/dataset/artquest","name":"ArtQuest","full_name":null,"description_markdown":"The task of Visual Question Answering (VQA) has been studied extensively on general-domain real-world images. Transferring insights from general domain VQA to the art domain (ArtVQA) is non-trivial, as the latter requires models to identify abstract concepts, details of brushstrokes and styles of paintings in the visual data as well as possess background knowledge about art. This is exacerbated by the lack of high-quality datasets. In this work, we shed light on hidden linguistic biases in the AQUA dataset, which is the only publicly available benchmark dataset for ArtVQA. As a result, the majority of questions can be answered without consulting the visual information, making the “V” in ArtVQA rather insignificant. In order to counter this problem, we create a simple, yet practical dataset, ArtQuest, using structured information from the SemArt collection. Our dataset and the pipeline to reproduce our results are publicly available at [https://github.com/bletib/artquest](https://github.com/bletib/artquest).","description_withheld":null,"homepage":"https://github.com/bletib/artquest","introduced_date":"2024-01-04","introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons Attribution 4.0 International","url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Art Analysis","url":"/task/art-analysis","datasets_with_task":"/datasets/task/art-analysis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ArtQuest"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-vqa-on-artquest","task":"Visual Question Answering (VQA)","dataset_variant":"ArtQuest","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"PrefixLM with CLIP and T5","paper":"/paper/artquest-countering-hidden-language-biases-in","metrics":{"1:1 Accuracy":"50.2"},"code_links":[{"title":"bletib/artquest","url":"https://github.com/bletib/artquest"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/artquest-countering-hidden-language-biases-in","title":"ArtQuest: Countering Hidden Language Biases in ArtVQA","date":"2024-01-04","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."}