{
 "id": "project-works/ComicVQA",
 "owner": "project-works",
 "name": "ComicVQA",
 "downloads": 365,
 "likes": 1,
 "last_modified": "2026-06-24T08:16:14.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{gan-etal-2026-comicvqa,\n    title = \"{C}omic{VQA}: A Benchmark for Visual Reasoning in Multimodal {LLM}s\",\n    author = \"Gan, Esther  and\n      Brown, Hannah  and\n      Herel, David  and\n      Kawaguchi, Kenji  and\n      Kan, Min-Yen  and\n      Shieh, Michael Qizhe\",\n    editor = \"Liakata, Maria  and\n      Moreira, Viviane P.  and\n      Zhang, Jiajun  and\n      Jurgens, David\",\n    booktitle = \"Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026\",\n    month = jul,\n    year = \"2026\",\n    address = \"San Diego, California, United States\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.findings-acl.1268/\",\n    pages = \"25347--25370\",\n    ISBN = \"979-8-89176-395-1\",\n    abstract = \"We introduce Comic Visual Question Answering (\\textbf{ComicVQA}), a comics-based benchmark for evaluating MLLMs on visual reasoning. ComicVQA comprises of (i) \\textbf{Missing Panel Prediction}, testing fine-grained visual grounding and (ii) \\textbf{Panel Sorting}, which evaluates sequential narrative understanding. Proprietary models achieve up to 62.6{\\%} on Missing Panel Prediction and 46.4{\\%} on Panel Sorting, whereas open-source models reach only 47.7{\\%} and 26.9{\\%}, respectively. In contrast, human annotators achieve over 83{\\%} accuracy on both tasks, revealing a large gap between current models and human-level multimodal understanding in comics. Through controlled ordering ablations and a detailed err",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "5a36582aa5e82d49b8ed7331f6276b876864ed6c",
 "stated_evidence": "https://huggingface.co/datasets/project-works/ComicVQA/blob/5a36582aa5e82d49b8ed7331f6276b876864ed6c/README.md",
 "file_evidence": "https://huggingface.co/datasets/project-works/ComicVQA/tree/5a36582aa5e82d49b8ed7331f6276b876864ed6c",
 "card_nc": false
}