{"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/measuring-visual-sycophancy-in-multimodal","title":"Measuring Agreeableness Bias in Multimodal Models","arxiv_id":"2408.09111","date":"2024-08-17","proceeding":null,"authors":["JaeHyuk Lim","Bruce W. Lee"],"abstract":"This paper examines a phenomenon in multimodal language models where pre-marked options in question images can significantly influence model responses. Our study employs a systematic methodology to investigate this effect: we present models with images of multiple-choice questions, which they initially answer correctly, then expose the same model to versions with pre-marked options. Our findings reveal a significant shift in the models' responses towards the pre-marked option, even when it contradicts their answers in the neutral settings. Comprehensive evaluations demonstrate that this agreeableness bias is a consistent and quantifiable behavior across various model architectures. These results show potential limitations in the reliability of these models when processing images with pre-marked options, raising important questions about their application in critical decision-making contexts where such visual cues might be present.","url_abs":"https://arxiv.org/abs/2408.09111v2","url_pdf":"https://arxiv.org/pdf/2408.09111v2.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":"measuring-visual-sycophancy-in-multimodal","repo_url":"https://github.com/jasonlim131/looksRdeceiving","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.09111","atlas_url":"https://app.syntology.ai/?focus=2408.09111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09111"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jasonlim131/looksRdeceiving","reach":null}],"summary":{"ran_draft_wrong":5,"ran_honours":3},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":0,"samples":[{"code_sha256_prefix":"0bcf62b801687bda","entry":"calculate_token_stats","repo":"jasonlim131/looksRdeceiving","repo_kind":"official","path":"python-src/evaluate_gpt4_v1.py","file_url":"https://github.com/jasonlim131/looksRdeceiving/blob/HEAD/python-src/evaluate_gpt4_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0bcf62b801687bda"}},{"code_sha256_prefix":"5f7a770e11dec715","entry":"count_answer_distribution","repo":"jasonlim131/looksRdeceiving","repo_kind":"official","path":"python-src/calculate_bias.py","file_url":"https://github.com/jasonlim131/looksRdeceiving/blob/HEAD/python-src/calculate_bias.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f7a770e11dec715"}},{"code_sha256_prefix":"b468df5b06b9a2c4","entry":"draw_choices","repo":"jasonlim131/looksRdeceiving","repo_kind":"official","path":"python-src/generate_vmmlu.py","file_url":"https://github.com/jasonlim131/looksRdeceiving/blob/HEAD/python-src/generate_vmmlu.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b468df5b06b9a2c4"}},{"code_sha256_prefix":"2d5f690652247562","entry":"encode_image","repo":"jasonlim131/looksRdeceiving","repo_kind":"official","path":"python-src/evaluate_gpt4_v1.py","file_url":"https://github.com/jasonlim131/looksRdeceiving/blob/HEAD/python-src/evaluate_gpt4_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d5f690652247562"}},{"code_sha256_prefix":"de6b6456d46ebea6","entry":"generate_html","repo":"jasonlim131/looksRdeceiving","repo_kind":"official","path":"python-src/generate_vmmlu.py","file_url":"https://github.com/jasonlim131/looksRdeceiving/blob/HEAD/python-src/generate_vmmlu.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de6b6456d46ebea6"}},{"code_sha256_prefix":"f2f7c5f5e999d421","entry":"generate_image","repo":"jasonlim131/looksRdeceiving","repo_kind":"official","path":"python-src/generate_vmmlu.py","file_url":"https://github.com/jasonlim131/looksRdeceiving/blob/HEAD/python-src/generate_vmmlu.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2f7c5f5e999d421"}},{"code_sha256_prefix":"14b7ffd0d2eba1af","entry":"load_data_for_variations","repo":"jasonlim131/looksRdeceiving","repo_kind":"official","path":"python-src/calculate_bias.py","file_url":"https://github.com/jasonlim131/looksRdeceiving/blob/HEAD/python-src/calculate_bias.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14b7ffd0d2eba1af"}},{"code_sha256_prefix":"4ce15e8de6e429ca","entry":"percent_correct","repo":"jasonlim131/looksRdeceiving","repo_kind":"official","path":"python-src/calculate_bias.py","file_url":"https://github.com/jasonlim131/looksRdeceiving/blob/HEAD/python-src/calculate_bias.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ce15e8de6e429ca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}