Go to ACL ARR 2025 February homepageDDxTutor: Clinical Reasoning Tutoring System with Differential Diagnosis-Based Structured Reasoning
Abstract: Clinical diagnosis education requires students to master both systematic reasoning processes and comprehensive medical knowledge. While recent advances in Large Language Models (LLMs) have enabled various medical educational applications, these systems often provide direct answers that reduce students' cognitive engagement and lead to fragmented learning. We propose DDxTutor, a framework that follows differential diagnosis principles to decompose clinical reasoning into teachable components, consisting of (1) a structured reasoning module that analyzes clinical clues and synthesizes diagnostic conclusions, and (2) an interactive dialogue system that guides students through this process. To enable such tutoring, we construct DDxReasoning, a dataset of 933 clinical cases with fine-grained diagnostic steps verified by doctors. Our experiments demonstrate that fine-tuned LLMs achieve strong performance in both generating structured teaching references and conducting interactive diagnostic tutoring dialogues. Human evaluation by medical educators and students validates the framework's effectiveness for clinical diagnosis education. Code and data will be available.
Paper Type: Long
Research Area: NLP Applications
Research Area Keywords: Medical Education, Dialogue System, Structured Reasoning
Contribution Types: Publicly available software and/or pre-trained models, Data resources
Languages Studied: English
Submission Number: 7385
Loading