{
 "id": "adonaivera/X-CASE",
 "owner": "adonaivera",
 "name": "X-CASE",
 "downloads": 25,
 "likes": 1,
 "last_modified": "2026-06-29T19:10:48.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification",
  "visual-question-answering"
 ],
 "citation": "@inproceedings{gonzalez-etal-2026-multimodal,\n    title = \"Multimodal Safety Evaluation in Generative Agent Social Simulations\",\n    author = \"Gonzalez, Alhim Adonai Vera  and\n      Hinojosa, Carlos  and\n      Sanchez, Karen  and\n      Hamid, Haidar Bin  and\n      Kim, Donghoon  and\n      Ghanem, Bernard\",\n    editor = \"Liakata, Maria  and\n      Moreira, Viviane P.  and\n      Zhang, Jiajun  and\n      Jurgens, David\",\n    booktitle = \"Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)\",\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.acl-long.1915/\",\n    pages = \"41295--41310\",\n    ISBN = \"979-8-89176-390-6\",\n    abstract = \"Can generative agents be trusted in multimodal environments? Despite recent advances, agents remain limited in their ability to reason about safety, coherence, and trust across modalities. We introduce a reproducible simulation framework to evaluate generative agents in three aspects: (1) safety improvement over time via iterative plan revision in multimodal scenarios; (2) detection of unsafe activities across social contexts; and (3) social dynamics, measured through interaction and acceptance rates. These multimodal agents are evaluated using metrics that quantify plan revisions and unsafe-to-safe conversions. Experiments show that while agents de",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "ddc7c3e6250a27cc2f2a816396678583841057f0",
 "stated_evidence": "https://huggingface.co/datasets/adonaivera/X-CASE/blob/ddc7c3e6250a27cc2f2a816396678583841057f0/README.md",
 "file_evidence": "https://huggingface.co/datasets/adonaivera/X-CASE/tree/ddc7c3e6250a27cc2f2a816396678583841057f0",
 "card_nc": false
}