{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/visbias-measuring-explicit-and-implicit","title":"VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models","arxiv_id":"2503.07575","date":"2025-03-10","proceeding":null,"authors":["Jen-tse Huang","Jiantong Qin","Jianping Zhang","Youliang Yuan","Wenxuan Wang","Jieyu Zhao"],"abstract":"This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional biases, while implicit bias operates subconsciously. To analyze explicit bias, we directly pose questions to VLMs related to gender and racial differences: (1) Multiple-choice questions based on a given image (e.g., \"What is the education level of the person in the image?\") (2) Yes-No comparisons using two images (e.g., \"Is the person in the first image more educated than the person in the second image?\") For implicit bias, we design tasks where VLMs assist users but reveal biases through their responses: (1) Image description tasks: Models are asked to describe individuals in images, and we analyze disparities in textual cues across demographic groups. (2) Form completion tasks: Models draft a personal information collection form with 20 attributes, and we examine correlations among selected attributes for potential biases. We evaluate Gemini-1.5, GPT-4V, GPT-4o, LLaMA-3.2-Vision and LLaVA-v1.6. Our code and data are publicly available at https://github.com/uscnlp-lime/VisBias.","url_abs":"https://arxiv.org/abs/2503.07575v2","url_pdf":"https://arxiv.org/pdf/2503.07575v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"visbias-measuring-explicit-and-implicit","repo_url":"https://github.com/uscnlp-lime/visbias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":null,"task_name":"Image Description"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.07575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07575"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uscnlp-lime/visbias","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/uscnlp-lime/VisBias","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"b379c91899319b8d","entry":"get_log_odds","repo":"uscnlp-lime/VisBias","repo_kind":"official","path":"code/image_description/marked_words.py","file_url":"https://github.com/uscnlp-lime/VisBias/blob/HEAD/code/image_description/marked_words.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b379c91899319b8d"}},{"code_sha256_prefix":"2828fa39419bb9a6","entry":"marked_words","repo":"uscnlp-lime/VisBias","repo_kind":"official","path":"code/image_description/marked_words.py","file_url":"https://github.com/uscnlp-lime/VisBias/blob/HEAD/code/image_description/marked_words.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2828fa39419bb9a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}