谁带来了飞盘：通过因果分析探究大型视觉-语言模型中的隐藏幻觉因素
Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis
AI总结：
本研究通过因果分析提出幻觉探测系统，识别并阻断大型视觉-语言模型中的隐藏幻觉因素，实验证明简单干预可显著减少幻觉输出。
摘要：
近期大型视觉-语言模型（LVLM）的进展显著增强了其结合自然语言理解视觉输入的能力。然而，其实际应用中的一个主要挑战是幻觉现象，即LVLM生成不存在的视觉元素，这削弱了用户的信任。驱动这种多模态幻觉的底层机制尚不明确。很少有研究阐明天空、树木或草地等上下文是否会导致LVLM产生飞盘的幻觉。我们假设隐藏因素，如对象、上下文以及语义前景-背景结构，会诱发幻觉。本研究提出了一种新颖的因果方法：一个幻觉探测系统，用于识别这些隐藏因素。通过分析图像、文本提示和网络显著性之间的因果关系，我们系统地探索了阻断这些因素的干预措施。我们的实验结果表明，基于我们分析的一种简单技术可以显著减少幻觉。此外，我们的分析表明，编辑网络内部结构以最小化幻觉输出具有潜力。
英文摘要：
Recent advancements in large vision-language models (LVLM) have significantly enhanced their ability to comprehend visual inputs alongside natural language. However, a major challenge in their real-world application is hallucination, where LVLMs generate non-existent visual elements, eroding user trust. The underlying mechanism driving this multimodal hallucination is poorly understood. Minimal research has illuminated whether contexts such as sky, tree, or grass field involve the LVLM in hallucinating a frisbee. We hypothesize that hidden factors, such as objects, contexts, and semantic foreground-background structures, induce hallucination. This study proposes a novel causal approach: a hallucination probing system to identify these hidden factors. By analyzing the causality between images, text prompts, and network saliency, we systematically explore interventions to block these factors. Our experimental findings show that a straightforward technique based on our analysis can significantly reduce hallucinations. Additionally, our analyses indicate the potential to edit network internals to minimize hallucinated outputs.
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。
