G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretation
2026-08-20 • Computation and Language
Computation and LanguageArtificial IntelligenceComputer Vision and Pattern Recognition
AI summaryⓘ
The authors highlight the need for medical reports to be explained in a way that is both accurate and easy for patients to understand. To solve this, they created a new task called PMRI, where models generate personalized explanations based on a patient's questions and previous conversations. They developed a new method, G-CARL, which uses detailed checks to make sure explanations are factually correct and meet patient needs without limiting creativity. They also built a benchmark dataset and evaluation system to test their approach. Their experiments show that G-CARL produces clearer and more accurate medical interpretations preferred by clinicians.
medical report interpretationmultimodal generationfactuality verificationreinforcement learningquery-based explanationchecklist supervisionpatient-centered communicationbenchmark datasetevaluation protocolclaim-level precision
Authors
Shiao Xie, Siyu Chen, Jianwei Lv, Bo Yuan, Yujin Wang, Xiandong Li
Abstract
Personalized interpretation of medical reports has emerged as an increasingly important need among patients. Addressing this need requires both evidence-grounded medical factuality and context-dependent patient communication, yet existing medical vision-language tasks do not adequately capture these dual requirements. To bridge this gap, we introduce Patient-oriented Medical Report Interpretation (PMRI), a novel open-ended multimodal generation task that requires models to explain medical reports in accurate and accessible language based on a user's query and dialogue history. These two objectives differ fundamentally in their verifiability, yet remain tightly coupled, making them difficult to optimize jointly under conventional supervised fine-tuning and holistic reinforcement learning paradigms. To address this challenge, we propose G-CARL, a grounded, checklist-aligned reinforcement learning framework that combines multi-source retrieval for atomic claim verification with context-aware, instance-specific weighted checklists for response coverage, providing structured supervision for factuality, user-demand satisfaction, and expression quality without constraining response diversity. We further construct MMedReport, a real-world PMRI benchmark, along with a clinician-designed three-dimensional evaluation protocol. Extensive experiments demonstrate that G-CARL consistently outperforms existing post-training baselines in overall quality, claim-level precision, and checklist recall. Pairwise preference evaluation by clinicians further confirms that G-CARL produces interpretations that are more accurate and better aligned with patient needs.