用因果干预揭示大模型幻觉根源，量化视觉上下文误导程度
Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
- 构建因果模型，识别训练中物体共现导致的虚假关联
- 设计反事实样本与指标，发现主流模型对虚假关联敏感度不一
- 提供可扩展的生成管道，适合研究模型鲁棒性与幻觉机制
大型视觉语言模型（LVLMs）常因训练中高度共现物体的虚假关联而产生对象幻觉，错误判断图像中物体的存在。现有基准多聚焦幻觉检测，缺乏对虚假关联的正式刻画与量化评估。本文引入因果分析，建立结构因果模型（SCM），形式化定义由共现偏差引发的虚假关联。为量化此类关联的影响，我们构建了Causal-HalBench基准，包含反事实样本并集成综合因果指标，用于评估模型对虚假关联的鲁棒性。同时提出可扩展的反事实样本生成流程，利用专有LVLM和文本到图像（T2I）模型生成。在主流LVLM上的评估表明，这些模型均表现出对虚假关联的易感性，但程度各异。
原文摘要 · Abstract (English)
Large Vision-Language Models (LVLMs) often suffer from object hallucination, making erroneous judgments about the presence of objects in images. We propose this primar- ily stems from spurious correlations arising when models strongly associate highly co-occurring objects during train- ing, leading to hallucinated objects influenced by visual con- text. Current benchmarks mainly focus on hallucination de- tection but lack a formal characterization and quantitative evaluation of spurious correlations in LVLMs. To address this, we introduce causal analysis into the object recognition scenario of LVLMs, establishing a Structural Causal Model (SCM). Utilizing the language of causality, we formally de- fine spurious correlations arising from co-occurrence bias. To quantify the influence induced by these spurious correla- tions, we develop Causal-HalBench, a benchmark specifically constructed with counterfactual samples and integrated with comprehensive causal metrics designed to assess model ro- bustness against spurious correlations. Concurrently, we pro- pose an extensible pipeline for the construction of these coun- terfactual samples, leveraging the capabilities of proprietary LVLMs and Text-to-Image (T2I) models for their genera- tion. Our evaluations on mainstream LVLMs using Causal- HalBench demonstrate these models exhibit susceptibility to spurious correlations, albeit to varying extents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。