Lie的解剖：一种多阶段诊断框架，用于追踪视觉-语言模型中的幻觉
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
AI总结：
本文提出一种多阶段诊断框架，通过动态认知轨迹分析视觉-语言模型中的幻觉问题，结合几何信息双重视角，实现高效且鲁棒的幻觉检测，提升模型透明度和可审计性。
摘要：
视觉-语言模型（VLMs）经常“幻觉”——生成看似合理但事实错误的陈述，成为其可信部署的关键障碍。本文提出一种新的诊断幻觉的范式，将幻觉从静态输出错误重新定义为模型计算认知的动态病理。我们的框架基于计算理性规范原则，将VLM的生成建模为动态认知轨迹。我们设计了一系列信息论探针，将轨迹投影到可解释的低维认知状态空间。我们的核心发现是几何-信息双重视角：轨迹在该空间中的几何异常性本质上等同于其高信息论意外性。幻觉检测被视为几何异常检测问题。在多样化的设置中，从严谨的二元问答（POPE）和全面推理（MME）到无约束的开放式描述（MS-COCO），我们的框架实现了最先进的性能。关键的是，它在弱监督下运行高效，并且即使校准数据严重污染时仍保持高度稳健。这种方法使失败原因得以归因，将可观察的错误映射到不同的病理状态：感知不稳定（通过感知熵测量）、逻辑-因果失败（通过推断冲突测量）和决策模糊（通过决策熵测量）。最终，这为构建其推理透明、可审计且可诊断的AI系统开辟了道路。
英文摘要：
Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this work, we propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition. Our framework is grounded in a normative principle of computational rationality, allowing us to model a VLM's generation as a dynamic cognitive trajectory. We design a suite of information-theoretic probes that project this trajectory onto an interpretable, low-dimensional Cognitive State Space. Our central discovery is a governing principle we term the geometric-information duality: a cognitive trajectory's geometric abnormality within this space is fundamentally equivalent to its high information-theoretic surprisal. Hallucination detection is counts as a geometric anomaly detection problem. Evaluated across diverse settings - from rigorous binary QA (POPE) and comprehensive reasoning (MME) to unconstrained open-ended captioning (MS-COCO) - our framework achieves state-of-the-art performance. Crucially, it operates with high efficiency under weak supervision and remains highly robust even when calibration data is heavily contaminated. This approach enables a causal attribution of failures, mapping observable errors to distinct pathological states: perceptual instability (measured by Perceptual Entropy), logical-causal failure (measured by Inferential Conflict), and decisional ambiguity (measured by Decision Entropy). Ultimately, this opens a path toward building AI systems whose reasoning is transparent, auditable, and diagnosable by design.
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。
