CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain

2026-03-05

AI Summary

This work addresses the challenges of terminology variability and noise in medical-domain Text-to-SQL tasks, where conventional retrieval-augmented approaches struggle to balance coverage and accuracy using static example pools. The authors propose CBR-to-SQL, a novel framework that introduces case-based reasoning (CBR) to this task by abstracting question–SQL pairs into reusable, structured case templates. A two-stage retrieval mechanism is designed: first matching logical structures and then resolving specific entities. This approach significantly enhances sample efficiency and robustness, achieving state-of-the-art logical form accuracy and competitive execution accuracy on the MIMICSQL dataset. Notably, it demonstrates superior performance under data-scarce conditions and in the presence of retrieval perturbations.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Intelligent Query Processing
• Machine Learning: Statistical Relational/Logic Learning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Extracting insights from Electronic Health Record (EHR) databases often requires SQL expertise, creating a barrier for healthcare decision-making and research. While a promising approach is to use Large Language Models (LLMs) to translate natural language questions to SQL via Retrieval-Augmented Generation (RAG), adapting this approach to the medical domain is non-trivial. Standard RAG relies on single-step retrieval from a static pool of examples, which struggles with the variability and noise of medical terminology and jargon. This often leads to anti-patterns such as expanding the task demonstration pool to improve coverage, which in turn introduces noise and scalability problems. To address this, we introduce CBR-to-SQL, a framework inspired by Case-Based Reasoning (CBR). It represents question-SQL pairs as reusable, abstract case templates and utilizes a two-stage retrieval process that first captures logical structure and then resolves relevant entities. Evaluated on MIMICSQL, CBR-to-SQL achieves state-of-the-art logical form accuracy and competitive execution accuracy. More importantly, it demonstrates higher sample efficiency and robustness than standard RAG approaches, particularly under data scarcity and retrieval perturbations.

Problem

• Text-to-SQL
• Electronic Health Records
• Retrieval-Augmented Generation
• Medical Domain
• Natural Language to SQL

Innovation

• Case-Based Reasoning
• Text-to-SQL
• Retrieval-Augmented Generation
• Two-stage Retrieval
• Healthcare Domain