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

Computer Science > Artificial Intelligence [Submitted on 21 Apr 2026] Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports Yishu Wei, Yi Lin, Adam Flanders, George Shih, Yifan Peng 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. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.19060 [cs.AI]   (or arXiv:2604.19060v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.19060 Focus to learn more Submission history From: Yishu Wei [view email] [v1] Tue, 21 Apr 2026 04:09:09 UTC (366 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)