针对胃肠道影像的幻觉问题，构建了带标注的高质量多模态数据集并提出新型纠错训练方法。
Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Models
- 用AI生成+专家校对构建带幻觉标记的胃肠道图像文本数据集
- 通过幻觉检测与纠正训练，显著降低模型生成错误描述的概率
- 为医疗视觉语言模型提供可复现的幻觉评估基准，适合医学AI研究者
视觉语言模型（VLMs）在医学领域日益普及，能理解医学图像与临床文本查询并生成详细诊断报告。然而，幻觉——即生成与图像内容不符的描述——仍是严重问题，尤其在医疗场景中后果严重。为此，我们构建了一个多模态图像-文本胃肠道数据集Gut-VLM，采用两阶段流程：首先用ChatGPT生成Kvasir-v2图像的描述报告，引入部分幻觉或错误文本；第二阶段由医学专家系统审查并修正不准确内容，确保标注高质量且临床可靠。该数据集不仅包含描述性文本，还标注了幻觉句子及其修正版本。传统减少幻觉的方法是微调模型生成报告，我们则提出‘幻觉感知微调’策略：让模型学习检测并纠正幻觉，而非仅生成报告。实验表明，该方法优于单纯生成报告的微调。我们还对多个主流VLM进行了全面评估，建立了基准。代码已开源。
原文摘要 · Abstract (English)
Vision-Language Models (VLMs) are becoming increasingly popular in the medical domain, bridging the gap between medical images and clinical language. Existing VLMs demonstrate an impressive ability to comprehend medical images and text queries to generate detailed, descriptive diagnostic medical reports. However, hallucination--the tendency to generate descriptions that are inconsistent with the visual content--remains a significant issue in VLMs, with particularly severe implications in the medical field. To facilitate VLM research on gastrointestinal (GI) image analysis and study hallucination, we curate a multimodal image-text GI dataset: Gut-VLM. This dataset is created using a two-stage pipeline: first, descriptive medical reports of Kvasir-v2 images are generated using ChatGPT, which introduces some hallucinated or incorrect texts. In the second stage, medical experts systematically review these reports, and identify and correct potential inaccuracies to ensure high-quality, clinically reliable annotations. Unlike traditional datasets that contain only descriptive texts, our dataset also features tags identifying hallucinated sentences and their corresponding corrections. A common approach to reducing hallucination in VLM is to finetune the model on a small-scale, problem-specific dataset. However, we take a different strategy using our dataset. Instead of finetuning the VLM solely for generating textual reports, we finetune it to detect and correct hallucinations, an approach we call hallucination-aware finetuning. Our results show that this approach is better than simply finetuning for descriptive report generation. Additionally, we conduct an extensive evaluation of state-of-the-art VLMs across several metrics, establishing a benchmark. GitHub Repo: https://github.com/bhattarailab/Hallucination-Aware-VLM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。