生成但验证：通过回顾性重采样减少视觉语言模型中的幻觉现象

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

April 17, 2025

作者: Tsung-Han Wu, Heekyung Lee, Jiaxin Ge, Joseph E. Gonzalez, Trevor Darrell, David M. Chan

cs.AI

摘要

视觉语言模型（VLMs）在视觉理解方面表现出色，但常常面临视觉幻觉问题，即生成对不存在物体、动作或概念的描述，这在安全关键应用中构成重大风险。现有的幻觉缓解方法通常遵循两种范式之一：生成调整，即修改解码行为以使文本与视觉输入对齐；以及事后验证，即通过外部模型评估并修正输出。尽管有效，生成调整方法往往依赖启发式规则且缺乏修正机制，而事后验证则较为复杂，通常需要多个模型，并倾向于拒绝输出而非精炼它们。在本研究中，我们引入了REVERSE，一个统一框架，将幻觉感知训练与实时自我验证相结合。通过利用包含超过130万半合成样本的新幻觉验证数据集，以及一种新颖的推理时回顾重采样技术，我们的方法使VLMs能够在生成过程中检测幻觉并动态修正这些幻觉。评估结果显示，REVERSE在减少幻觉方面达到了最先进水平，在CHAIR-MSCOCO上比现有最佳方法高出12%，在HaloQuest上高出28%。我们的数据集、模型及代码可在以下网址获取：https://reverse-vlm.github.io。

English

Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations, where they generate descriptions of nonexistent objects, actions, or concepts, posing significant risks in safety-critical applications. Existing hallucination mitigation methods typically follow one of two paradigms: generation adjustment, which modifies decoding behavior to align text with visual inputs, and post-hoc verification, where external models assess and correct outputs. While effective, generation adjustment methods often rely on heuristics and lack correction mechanisms, while post-hoc verification is complicated, typically requiring multiple models and tending to reject outputs rather than refine them. In this work, we introduce REVERSE, a unified framework that integrates hallucination-aware training with on-the-fly self-verification. By leveraging a new hallucination-verification dataset containing over 1.3M semi-synthetic samples, along with a novel inference-time retrospective resampling technique, our approach enables VLMs to both detect hallucinations during generation and dynamically revise those hallucinations. Our evaluations show that REVERSE achieves state-of-the-art hallucination reduction, outperforming the best existing methods by up to 12% on CHAIR-MSCOCO and 28% on HaloQuest. Our dataset, model, and code are available at: https://reverse-vlm.github.io.