大型视觉-语言模型中的幻觉综述
A Survey on Hallucination in Large Vision-Language Models
AI总结：
本文系统综述了大型视觉-语言模型中的幻觉问题，涵盖概念界定、评估基准、根本原因与缓解方法，并提出未来研究方向。
摘要：
近年来，大型视觉-语言模型（LVLMs）的发展因其实际应用潜力而在人工智能领域引起了越来越多的关注。然而，“幻觉”，更具体地说，是事实性视觉内容与相应文本生成之间的不一致，对利用LVLMs构成了重大挑战。在这篇综合性综述中，我们剖析了与LVLM相关的幻觉，旨在建立一个总体概览并促进未来的缓解工作。我们的审视首先从澄清LVLMs中幻觉的概念开始，呈现了多种幻觉症状，并强调了LVLM幻觉中固有的独特挑战。随后，我们概述了专门为评估LVLMs特有幻觉而量身定制的基准和方法。此外，我们深入调查了这些幻觉的根本原因，包括来自训练数据和模型组件的见解。我们还批判性地回顾了现有的幻觉缓解方法。最后，我们讨论了LVLMs中幻觉相关的开放性问题和未来方向，以总结本综述。
英文摘要：
Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between factual visual content and corresponding textual generation, poses a significant challenge of utilizing LVLMs. In this comprehensive survey, we dissect LVLM-related hallucinations in an attempt to establish an overview and facilitate future mitigation. Our scrutiny starts with a clarification of the concept of hallucinations in LVLMs, presenting a variety of hallucination symptoms and highlighting the unique challenges inherent in LVLM hallucinations. Subsequently, we outline the benchmarks and methodologies tailored specifically for evaluating hallucinations unique to LVLMs. Additionally, we delve into an investigation of the root causes of these hallucinations, encompassing insights from the training data and model components. We also critically review existing methods for mitigating hallucinations. The open questions and future directions pertaining to hallucinations within LVLMs are discussed to conclude this survey.
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。
