大型视觉语言模型中幻觉现象的成因探究与缓解策略
Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models
AI总结：
本研究分析大型视觉语言模型在图像字幕生成中的幻觉模式，利用图像依赖性信号训练词元级分类器，并提出解码策略以在推理时控制幻觉率。
摘要：
大型视觉语言模型（LVLMs）将图像编码器与大型语言模型（LLMs）集成，以处理多模态输入并执行复杂的视觉任务。然而，它们常常通过描述不存在的物体或属性而产生幻觉，从而损害其可靠性。本研究分析了图像字幕生成中的幻觉模式，表明生成过程中的并非所有词元都受图像输入影响，且图像依赖性可作为幻觉检测的有效信号。为解决此问题，我们开发了一个自动化流程来识别幻觉物体，并利用来自并行推理过程（有图像输入和无图像输入）的隐藏表示训练了一个词元级分类器。借助该分类器，我们提出了一种解码策略，可在推理时有效控制图像字幕生成中的幻觉率。
英文摘要：
Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects or attributes, compromising their reliability. This study analyzes hallucination patterns in image captioning, showing that not all tokens in the generation process are influenced by image input and that image dependency can serve as a useful signal for hallucination detection. To address this, we develop an automated pipeline to identify hallucinated objects and train a token-level classifier using hidden representations from parallel inference passes-with and without image input. Leveraging this classifier, we introduce a decoding strategy that effectively controls hallucination rates in image captioning at inference time.
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。
