基于上下文感知物体相似度评估大型视觉语言模型中的幻觉
Evaluating Hallucination in Large Vision-Language Models based on Context-Aware Object Similarities
AI总结：
提出CAOS评估框架，结合物体统计与语义关系，利用语言模型识别域外物体并验证，系统量化并解释大型视觉语言模型的物体幻觉。
摘要：
尽管大型视觉语言模型（LVLMs）在多模态任务上表现出色，但它们往往会产生幻觉。一种重要的类型是物体幻觉，即LVLMs生成与展示给模型的图像不一致的物体。现有工作通常试图通过检测并测量生成描述中幻觉物体的比例来量化物体幻觉。此外，最新研究还通过基于物体统计信息（如top-k频繁出现的物体和top-k共现物体），直接向LVLM提出关于可能产生幻觉的物体是否存在的二元问题来测量物体幻觉。在本文中，我们提出了一种基于上下文感知物体相似度（CAOS）的新方法，利用物体统计信息以及生成的描述来评估LVLMs中的物体幻觉。CAOS独特地将物体统计信息与描述中物体及真实数据之间的语义关系结合在一起。此外，现有方法通常仅检测和测量属于预定义的域内物体集合（通常是训练数据集的所有真实物体集合）的幻觉，并忽略不属于该集合的生成物体，从而导致评估不足。为了解决这一问题，我们进一步采用基于语言模型的物体识别来检测潜在的域外幻觉物体，并使用LVLMs集合来验证此类物体是否存在于查询图像中。CAOS还检查了物体生成的序列动态，揭示了物体出现顺序如何影响幻觉，并采用词嵌入模型来分析幻觉背后的语义原因。CAOS旨在通过提供一个识别和解释物体幻觉的系统框架，为LVLMs的幻觉倾向提供细致的理解。
英文摘要：
Despite their impressive performance on multi-modal tasks, large vision-language models (LVLMs) tend to suffer from hallucinations. An important type is object hallucination, where LVLMs generate objects that are inconsistent with the images shown to the model. Existing works typically attempt to quantify object hallucinations by detecting and measuring the fraction of hallucinated objects in generated captions. Additionally, more recent work also measures object hallucinations by directly querying the LVLM with binary questions about the presence of likely hallucinated objects based on object statistics like top-k frequent objects and top-k co-occurring objects. In this paper, we present Context-Aware Object Similarities (CAOS), a novel approach for evaluating object hallucination in LVLMs using object statistics as well as the generated captions. CAOS uniquely integrates object statistics with semantic relationships between objects in captions and ground-truth data. Moreover, existing approaches usually only detect and measure hallucinations belonging to a predetermined set of in-domain objects (typically the set of all ground-truth objects for the training dataset) and ignore generated objects that are not part of this set, leading to under-evaluation. To address this, we further employ language model--based object recognition to detect potentially out-of-domain hallucinated objects and use an ensemble of LVLMs for verifying the presence of such objects in the query image. CAOS also examines the sequential dynamics of object generation, shedding light on how the order of object appearance influences hallucinations, and employs word embedding models to analyze the semantic reasons behind hallucinations. CAOS aims to offer a nuanced understanding of the hallucination tendencies of LVLMs by providing a systematic framework to identify and interpret object hallucinations.
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。
