mlsanityData to 14 Oct 2026

Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports

arXiv 2604.19060 ↗First posted 21 Apr 2026cs.AIcited by 2

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improves accuracy, it can degrade reasoning. We propose a two-stage approach: SFT on disease labels followed by Group Relative Policy Optimization (GRPO) to refine predictions by optimizing accuracy and format without reasoning supervision. Across three radiologist-annotated datasets, SFT outperformed baselines and GRPO further improved classification and enhanced reasoning recall and comprehensiveness.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 21 of its 30 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

21 of 30 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification29 Apr

Other references · 20

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  6. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  7. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  8. 2024A Survey on LLM-as-a-Judgecited by 1,423
  9. 2019Publicly Available Clinical BERT Embeddingscited by 1,002
  10. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  11. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 597
  12. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 319
8 more
  1. 2023MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Datacited by 286
  2. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 160
  3. 2024CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formatscited by 106
  4. 2024RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Foldcited by 99
  5. 2023CPLLM: Clinical Prediction with Large Language Modelscited by 34
  6. 2023BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processingcited by 25
  7. 2025The Rise of Small Language Models in Healthcare: A Comprehensive Surveycited by 18
  8. 2024Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labelscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Modelscited by 0
  2. 2026ChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reportscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation
  2. 2025Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning
  3. 2026HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize
  4. 2026Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning
  5. 2025OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
  6. 2026Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning
  7. 2025EditGRPO: Reinforcement Learning with Post-Rollout Edits for Clinically Accurate Chest X-Ray Report Generation
  8. 2025Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation