Towards Explainable Diagnosis: A Self-learned Explanatory Knowledge Base Approach

ACL ARR 2025 May Submission7727 Authors

Abstract: Explainable diagnosis requires the process of reaching diagnostic conclusions with clear rationale that links a patient’s clinical phenomenon to authoritative medical knowledge. While large language models (LLMs) show promise in supporting explainable diagnosis, they often fall short due to insufficient diagnostic knowledge. To address this limitation, we propose Self-learned Explainable Knowledge Augmented Diagnosis (SEKAD), a unified LLM-based framework for faithful and explainable diagnosis. Our approach builds a high-quality diagnostic knowledge base through a record-driven explanation learning paradigm, as well as applies this knowledge via an explanation-based diagnostic process that ensures faithful inference. Experiments on the DiReCT and JAMA benchmarks show that SEKAD consistently outperforms strong baselines across the metrics. In particular, SEKAD achieves absolute improvement of 12.4% in the completeness of explanation metric over the best existing methods, highlighting its effectiveness in enhancing diagnostic explainability.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: Information Retrieval and Text Mining, NLP Applications

Languages Studied: English

Submission Number: 7727