基于短语视觉定位的自动偏好优化用于改进胸部X光报告生成
Phrase-grounded APO for Improving Chest X-ray Report Generation
提出一种无需真值偏好对的自动偏好优化方法，通过事实核查和LLM提示纠正生成代理偏好数据，并设计结合短语视觉定位损失的APO损失函数，可提升视觉语言模型在推理时的报告事实正确性。
原文依据 phrase-grounded automatic preference optimization (APO) alignment method
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自动放射学报告生成（RRG）模型在临床工作流中的部署正受到所生成报告缺乏事实正确性的阻碍。现有改进报告生成器的方法使用对齐方法，这些方法需要成对的真值偏好和非偏好响应。由于这些在临床工作流的推理时不可用，因此需要新的对齐方法在推理时提升报告质量。本文提出一种新的基于短语视觉定位的自动偏好优化（APO）对齐方法，该方法在推理时无需额外真值即可提供此类改进。具体而言，该方法通过事实核查和LLM提示纠正，从RRG模型响应本身自动生成代理真值偏好数据用于对齐。我们还开发了一种新的APO损失函数，将偏好响应对齐损失与短语视觉定位损失相结合，同时关注发现的描述及其图像位置。我们证明，这种对齐方法在多个机构的胸部X光数据集上测试时，平均将各种最先进报告生成器在推理时的报告质量提升30-40%。
英文原文摘要 1245 字符
The deployment of automatic radiology report generator (RRG) models in clinical workflows is being hampered by the lack of factual correctness in the produced reports. Existing methods to improve the report generators use alignment approaches that require pairs of ground truth preferred and dis-preferred responses. As these are not available at inference time in clinical workflows, new alignment methods are needed to improve report quality at inference time. In this paper, we present a new phrase-grounded automatic preference optimization (APO) alignment method which offers such improvement during inference without needing additional ground truth. Specifically, the method generates surrogate ground truth preference data for alignment automatically from the RRG model response itself though fact-checking and LLM-prompted correction. We also develop a novel APO loss function that combines preference response alignment loss with phrasal grounding loss paying attention to both the description of the finding and its image location. We show that this method of alignment, on the average, improves the report quality at inference time by 30-40% across various SOTA report generators as tested on multi-institutional chest X-ray datasets.