LEAD：逐层专家对齐解码以生成准确的放射学报告
LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation
AI总结：
LEAD通过逐层专家对齐解码方法，提升放射学报告生成的准确性并减少幻觉。
摘要：
放射学报告生成（RRG）旨在从医学图像中生成准确且连贯的诊断。尽管大型视觉语言模型（LVLM）提高了报告的流畅性和准确性，但它们会生成看似合理但图像不支持的病理细节。现有方法主要依赖外部知识指导来促进生成文本与视觉信息之间的对齐。然而，这些方法往往忽略了预训练模型中固有的解码先验和视觉语言对齐偏差，并且由于依赖于构造的指导而缺乏鲁棒性。在本文中，我们提出了逐层专家对齐解码（LEAD），一种新的方法，以内在地修改LVLM的解码轨迹。设计了一个多专家模块，用于提取不同的病理特征，这些特征通过门控机制整合到每个解码器层中。这种逐层架构使LLM能够在每个推理步骤中通过学习的门控函数咨询专家特征，从而动态修正解码偏差并引导生成朝着事实一致性发展。在多个公开数据集上的实验表明，LEAD方法在临床准确性指标上取得了有效的提升，并在减轻幻觉的同时保持了高质量的生成。
英文摘要：
Radiology Report Generation aims to produce accurate and coherent diagnostics from medical images. Although large vision-language models improve report fluency and accuracy, they still suffer from hallucinations by generating plausible pathological descriptions that are not supported by the input images. Existing methods primarily rely on external knowledge guidance to facilitate the alignment between generated text and visual information. However, these approaches often ignore the inherent decoding priors and vision-language alignment biases in pretrained models and lack robustness due to reliance on constructed guidance. In this paper, we propose Layer-wise Expert-aligned Decoding, a method that directly intervenes in the internal decoding process of large vision-language models. A pathology-specific expert module is designed to extract discriminative pathological features, which are then injected into each decoder layer through a gated mechanism. This architecture enables the large language model to progressively incorporate expert features during generation through a learned layer-wise gating function, thereby mitigating decoding biases and steering generation toward factual consistency. Experiments on multiple public datasets demonstrate that the proposed method improves clinical accuracy and factual consistency while maintaining competitive report generation quality.
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。
