对齐发现与诊断：一种自洽的强化学习框架用于可信的放射学报告
HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize
AI总结：
本文提出了一种自洽的强化学习框架，用于生成可信的放射学报告，通过优化生成过程和减少幻觉，提升了临床效果。
摘要：
多模态大语言模型（MLLMs）在放射学报告生成中展现出强大的潜力，但其临床应用受到架构异质性和事实性幻觉的阻碍。标准的监督微调往往无法严格对齐语言输出与视觉证据，而现有的强化学习方法则在计算成本或探索有限方面存在困难。为了解决这些挑战，我们提出了一种全面的框架用于自洽的放射学报告生成。首先，我们进行系统评估以确定最佳的视觉编码器和LLM主干配置用于医学影像。在此基础上，我们引入了一种新的
英文摘要：
Multimodal Large Language Models (MLLMs) have substantially advanced Radiology Report Generation (RRG), yet aligning them through reinforcement learning (RL) remains challenging due to heterogeneous medical supervision. Vanilla Group Relative Policy Optimization (GRPO) assigns uniform credit across the entire generation, leading to segment interference, token dilution, and evidence--diagnosis decoupling, which exacerbates clinical hallucinations. We propose HERO (Hierarchical Evidential Reasoning Optimization), a factorized policy optimization framework that aligns heterogeneous supervision with three optimization granularities. HERO separately optimizes reasoning, diagnosis, and evidence grounding through complementary segment-, token-, and completion-level optimization with a heterogeneous reward formulation covering diagnostic accuracy, reasoning quality, and think--answer consistency. Experiments on MIMIC-CXR and IU-Xray show that HERO outperforms strong supervised and reinforcement learning baselines, achieving state-of-the-art clinical efficacy while producing more evidence-grounded and think--answer-consistent reports, thereby substantially mitigating clinical hallucinations.
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。
