CaseGPT: a case reasoning framework based on language models and retrieval-augmented generation
Rui Yang
TL;DR
The paper tackles the difficulty of case-based reasoning in medicine and law due to massive, imprecise case data and unstructured queries. It introduces CaseGPT, a framework that fuses Large Language Models with Retrieval-Augmented Generation to enable fuzzy semantic search and to generate context-aware insights from retrieved cases. Across medical and legal datasets, CaseGPT outperforms keyword-based and simple LLM baselines in retrieval precision, recall, and efficiency, while also delivering higher-quality, actionable insights from professionals. The work highlights practical impact, ethical considerations, and a roadmap for future enhancements to responsibly deploy AI-assisted case reasoning tools.
Abstract
This paper presents CaseGPT, an innovative approach that combines Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) technology to enhance case-based reasoning in the healthcare and legal sectors. The system addresses the challenges of traditional database queries by enabling fuzzy searches based on imprecise descriptions, thereby improving data searchability and usability. CaseGPT not only retrieves relevant case data but also generates insightful suggestions and recommendations based on patterns discerned from existing case data. This functionality proves especially valuable for tasks such as medical diagnostics, legal precedent research, and case strategy formulation. The paper includes an in-depth discussion of the system's methodology, its performance in both medical and legal domains, and its potential for future applications. Our experiments demonstrate that CaseGPT significantly outperforms traditional keyword-based and simple LLM-based systems in terms of precision, recall, and efficiency.