Explainable Disease Diagnosis with LLMs and ASP
Published:Dec 30, 2025 01:32
•1 min read
•ArXiv
Analysis
This paper addresses the challenge of explainable AI in healthcare by combining the strengths of Large Language Models (LLMs) and Answer Set Programming (ASP). It proposes a framework, McCoy, that translates medical literature into ASP code using an LLM, integrates patient data, and uses an ASP solver for diagnosis. This approach aims to overcome the limitations of traditional symbolic AI in healthcare by automating knowledge base construction and providing interpretable predictions. The preliminary results suggest promising performance on small-scale tasks.
Key Takeaways
Reference
“McCoy orchestrates an LLM to translate medical literature into ASP code, combines it with patient data, and processes it using an ASP solver to arrive at the final diagnosis.”