# HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize

arXiv: https://arxiv.org/abs/2601.03321 · HTML: https://mlsanity.com/paper/2601.03321/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 14 of its 45 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 14 of 14)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://mlsanity.com/paper/2004.09167/) (2020)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [Detecting and Evaluating Medical Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2406.10185/) (2024)
- [GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy](https://mlsanity.com/paper/2508.04349/) (2025)
- [Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement](https://mlsanity.com/paper/2403.06728/) (2024)
- [X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation](https://mlsanity.com/paper/2406.17911/) (2024)
- [R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression](https://mlsanity.com/paper/2512.18986/) (2025)

## Built on by (most cited first, 3 of 3)

- [Motion-Aware Caching for Efficient Autoregressive Video Generation](https://mlsanity.com/paper/2605.01725/) (2026)
- [ChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reports](https://mlsanity.com/paper/2609.31629/) (2026)
- [A Deterministic Evidence Layer for Vision-Language Autism Screening from Naturalistic Home Video](https://mlsanity.com/paper/2610.09217/) (2026)

## Abstract (arXiv)

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 rationale-diagnosis decoupling, which exacerbates clinical hallucinations. We propose HERO (Hierarchical rationalE Reasoning Optimization), a factorized policy optimization framework that aligns heterogeneous supervision with three optimization granularities. HERO separately optimizes reasoning, diagnosis, and rationale faithfulness 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 rationale-supported and think-answer-consistent reports, thereby substantially mitigating clinical hallucinations.