Work

Reinforcement learning improves LLM accuracy and reasoning in disease classification from radiology reports

Year: 2026

Type: article

Abstract: 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.

Source: npj Digital Medicine

DOI: 10.1038/s41746-026-02685-4

Authors: Yishu Wei, Yi Lin, Adam Flanders, George Shih, Yifan Peng

Institutions: Weill Cornell Medicine, Thomas Jefferson University

Language: English

Topic: Machine Learning in Healthcare

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $4,090