SegSub：评估视觉-语言模型对知识冲突与幻觉的鲁棒性
SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models
AI总结：
本文提出 SegSub 框架，通过图像扰动系统评估视觉-语言模型在知识冲突下的幻觉脆弱性，并通过微调提升冲突检测能力。
摘要：
视觉-语言模型（VLM）展示了复杂的多模态推理能力，但在面对知识冲突时容易产生幻觉，阻碍了其在信息敏感场景中的部署。现有研究主要关注单模态模型的鲁棒性，而多模态领域缺乏对跨模态知识冲突的系统性研究。本研究引入了 SegSub 框架，通过施加有针对性的图像扰动来考察 VLM 对知识冲突的抵抗能力。我们的分析揭示了不同的脆弱性模式：虽然 VLM 对参数化冲突具有鲁棒性（20% 的遵循率），但它们在识别反事实条件（<30% 准确率）和解决来源冲突（<1% 准确率）方面表现出显著弱点。上下文丰富度与幻觉率之间的相关性（r = -0.368，p = 0.003）揭示了哪些类型的图像可能引发幻觉。通过在我们的基准数据集上进行有针对性的微调，我们证明了 VLM 知识冲突检测能力的提升，为在信息敏感环境中开发抗幻觉的多模态系统奠定了基础。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
