HalCECE：一种在图像描述任务中通过概念反事实实现可解释幻觉检测的框架
HalCECE: A Framework for Explainable Hallucination Detection through Conceptual Counterfactuals in Image Captioning
AI总结：
本研究针对视觉-语言模型的幻觉检测问题，提出可解释框架HalCECE，基于概念反事实生成语义最小编辑，结合层级概念分解与角色幻觉分析，为VL系统可信评估提供新方向。
摘要：
在人工智能的动态发展格局中，视觉-语言（VL）模型的幻觉问题研究已成为关键前沿领域。本工作深入探究了广泛使用的图像描述模型所呈现的幻觉现象的复杂机制，揭示了若干有趣的规律。具体而言，我们采用此前提出的概念反事实解释技术来解决视觉-语言幻觉问题。所采用的概念反事实主干具有确定性与高效性，能够基于层级化知识生成语义上最小程度的编辑，从而以黑盒方式实现从幻觉描述到非幻觉描述的转换。我们提出的幻觉检测框架HalCECE具有高度可解释性，除了独立数值结果外，还能提供语义层面有意义的编辑方案，同时通过对幻觉概念的层级分解实现全面的幻觉分析。本工作的另一项创新点是对角色幻觉的探究，是首批将视觉概念间的关联纳入幻觉检测研究的工作之一。总体而言，HalCECE为视觉-语言幻觉检测这一重要领域提供了一条可解释的研究方向，从而助力对当前及未来视觉-语言系统的可信评估。
英文摘要：
In the dynamic landscape of artificial intelligence, the exploration of hallucinations within vision-language (VL) models emerges as a critical frontier. This work delves into the intricacies of hallucinatory phenomena exhibited by widely used image captioners, unraveling interesting patterns. Specifically, we step upon previously introduced techniques of conceptual counterfactual explanations to address VL hallucinations. The deterministic and efficient nature of the employed conceptual counterfactuals backbone is able to suggest semantically minimal edits driven by hierarchical knowledge, so that the transition from a hallucinated caption to a non-hallucinated one is performed in a black-box manner. HalCECE, our proposed hallucination detection framework is highly interpretable, by providing semantically meaningful edits apart from standalone numbers, while the hierarchical decomposition of hallucinated concepts leads to a thorough hallucination analysis. Another novelty tied to the current work is the investigation of role hallucinations, being one of the first works to involve interconnections between visual concepts in hallucination detection. Overall, HalCECE recommends an explainable direction to the crucial field of VL hallucination detection, thus fostering trustworthy evaluation of current and future VL systems.
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。
