{"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/segsub-evaluating-robustness-to-knowledge","title":"SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models","arxiv_id":"2502.14908","date":"2025-02-19","proceeding":null,"authors":["Peter Carragher","Nikitha Rao","Abhinand Jha","R Raghav","Kathleen M. Carley"],"abstract":"Vision language models (VLM) demonstrate sophisticated multimodal reasoning yet are prone to hallucination when confronted with knowledge conflicts, impeding their deployment in information-sensitive contexts. While existing research addresses robustness in unimodal models, the multimodal domain lacks systematic investigation of cross-modal knowledge conflicts. This research introduces \\segsub, a framework for applying targeted image perturbations to investigate VLM resilience against knowledge conflicts. Our analysis reveals distinct vulnerability patterns: while VLMs are robust to parametric conflicts (20% adherence rates), they exhibit significant weaknesses in identifying counterfactual conditions (<30% accuracy) and resolving source conflicts (<1% accuracy). Correlations between contextual richness and hallucination rate (r = -0.368, p = 0.003) reveal the kinds of images that are likely to cause hallucinations. Through targeted fine-tuning on our benchmark dataset, we demonstrate improvements in VLM knowledge conflict detection, establishing a foundation for developing hallucination-resilient multimodal systems in information-sensitive environments.","url_abs":"https://arxiv.org/abs/2502.14908v2","url_pdf":"https://arxiv.org/pdf/2502.14908v2.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":"segsub-evaluating-robustness-to-knowledge","repo_url":"https://github.com/CASOS-IDeaS-CMU/SegSub","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[{"slug":"segsub","name":"SegSub","full_name":"SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}