{"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/better-safe-than-sorry-overreaction-problem","title":"Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition","arxiv_id":"2505.15367","date":"2025-05-21","proceeding":null,"authors":["Dasol Choi","SeungHyun Lee","YoungSook Song"],"abstract":"Vision-Language Models (VLMs) have demonstrated impressive capabilities in understanding visual content, but their reliability in safety-critical contexts remains under-explored. We introduce VERI (Visual Emergency Recognition Dataset), a carefully designed diagnostic benchmark of 200 images (100 contrastive pairs). Each emergency scene is matched with a visually similar but safe counterpart through multi-stage human verification and iterative refinement. Using a two-stage protocol - risk identification and emergency response - we evaluate 14 VLMs (2B-124B parameters) across medical emergencies, accidents, and natural disasters. Our analysis reveals a systematic overreaction problem: models excel at identifying real emergencies (70-100 percent success rate) but suffer from an alarming rate of false alarms, misidentifying 31-96 percent of safe situations as dangerous, with 10 scenarios failed by all models regardless of scale. This \"better-safe-than-sorry\" bias manifests primarily through contextual overinterpretation (88-93 percent of errors), challenging VLMs' reliability for safety applications. These findings highlight persistent limitations that are not resolved by increasing model scale, motivating targeted approaches for improving contextual safety assessment in visually misleading scenarios.","url_abs":"https://arxiv.org/abs/2505.15367v1","url_pdf":"https://arxiv.org/pdf/2505.15367v1.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":"better-safe-than-sorry-overreaction-problem","repo_url":"https://github.com/Dasol-Choi/VERI-Emergency","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.15367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15367"}},"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/Dasol-Choi/VERI-Emergency","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"ran":0,"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":"7a5b1763464358b6","entry":"analyze_q1_performance","repo":"Dasol-Choi/VERI-Emergency","repo_kind":"listed","path":"src/comprehensive_analysis.py","file_url":"https://github.com/Dasol-Choi/VERI-Emergency/blob/HEAD/src/comprehensive_analysis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a5b1763464358b6"}},{"code_sha256_prefix":"90aaf85d33aa2c99","entry":"analyze_q2_performance","repo":"Dasol-Choi/VERI-Emergency","repo_kind":"listed","path":"src/comprehensive_analysis.py","file_url":"https://github.com/Dasol-Choi/VERI-Emergency/blob/HEAD/src/comprehensive_analysis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90aaf85d33aa2c99"}},{"code_sha256_prefix":"b2b5e38f21284259","entry":"get_emergency_images_from_q1","repo":"Dasol-Choi/VERI-Emergency","repo_kind":"listed","path":"src/q2_evaluation.py","file_url":"https://github.com/Dasol-Choi/VERI-Emergency/blob/HEAD/src/q2_evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2b5e38f21284259"}},{"code_sha256_prefix":"97b42126caf28fdc","entry":"load_dataset_images","repo":"Dasol-Choi/VERI-Emergency","repo_kind":"listed","path":"src/q2_evaluation.py","file_url":"https://github.com/Dasol-Choi/VERI-Emergency/blob/HEAD/src/q2_evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97b42126caf28fdc"}},{"code_sha256_prefix":"55325907ea1100df","entry":"load_model","repo":"Dasol-Choi/VERI-Emergency","repo_kind":"listed","path":"src/q1_evaluation.py","file_url":"https://github.com/Dasol-Choi/VERI-Emergency/blob/HEAD/src/q1_evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55325907ea1100df"}},{"code_sha256_prefix":"a5e33150bd3e4125","entry":"load_results","repo":"Dasol-Choi/VERI-Emergency","repo_kind":"listed","path":"src/comprehensive_analysis.py","file_url":"https://github.com/Dasol-Choi/VERI-Emergency/blob/HEAD/src/comprehensive_analysis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5e33150bd3e4125"}},{"code_sha256_prefix":"1d62f67962db5bc8","entry":"parse_safety_prediction","repo":"Dasol-Choi/VERI-Emergency","repo_kind":"listed","path":"src/q1_evaluation.py","file_url":"https://github.com/Dasol-Choi/VERI-Emergency/blob/HEAD/src/q1_evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d62f67962db5bc8"}},{"code_sha256_prefix":"f807be36560163f0","entry":"run_q1_evaluation","repo":"Dasol-Choi/VERI-Emergency","repo_kind":"listed","path":"src/q1_evaluation.py","file_url":"https://github.com/Dasol-Choi/VERI-Emergency/blob/HEAD/src/q1_evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f807be36560163f0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}