GLSim：通过全局-局部相似性检测LVLM中的对象幻觉
GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
AI总结：
GLSim提出一种免训练的对象幻觉检测框架，通过融合全局与局部嵌入相似性信号，显著提升了大视觉语言模型中对象幻觉检测的准确性和可靠性。
摘要：
大型视觉语言模型中的对象幻觉对其在现实世界应用中的安全部署构成了重大挑战。近期工作提出了对象级幻觉分数来估计对象幻觉的可能性；然而，这些方法通常孤立地采用全局或局部视角，这可能限制检测的可靠性。在本文中，我们引入了GLSim，一种新颖的免训练对象幻觉检测框架，该框架利用图像和文本模态之间互补的全局和局部嵌入相似性信号，从而在多样场景中实现更准确和可靠的幻觉检测。我们对现有的对象幻觉检测方法进行了全面基准测试，并证明GLSim取得了优越的检测性能，显著超越了竞争性基线方法。
英文摘要：
Object hallucination in large vision-language models presents a significant challenge to their safe deployment in real-world applications. Recent works have proposed object-level hallucination scores to estimate the likelihood of object hallucination; however, these methods typically adopt either a global or local perspective in isolation, which may limit detection reliability. In this paper, we introduce GLSim, a novel training-free object hallucination detection framework that leverages complementary global and local embedding similarity signals between image and text modalities, enabling more accurate and reliable hallucination detection in diverse scenarios. We comprehensively benchmark existing object hallucination detection methods and demonstrate that GLSim achieves superior detection performance, outperforming competitive baselines by a significant margin.
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。
