KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR
This work addresses the problem of robust data retrieval from EHR databases for healthcare professionals, though it is incremental as it builds on existing LLM methods with templatization and verification.
The paper tackles the challenge of detecting and rejecting unanswerable questions in natural language to SQL query generation for electronic health record databases, introducing a framework that uses question templatization and query execution verification to improve adaptability and achieve competitive performance on the EHRSQL-2024 benchmark.
Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this process is detecting and rejecting unanswerable questions that request information beyond the database's scope or exceed the system's capabilities. In this paper, we introduce a novel text-to-SQL framework that robustly handles out-of-domain questions and verifies the generated queries with query execution.Our framework begins by standardizing the structure of questions into a templated format. We use a powerful large language model (LLM), fine-tuned GPT-3.5 with detailed prompts involving the table schemas of the EHR database system. Our experimental results demonstrate the effectiveness of our framework on the EHRSQL-2024 benchmark benchmark, a shared task in the ClinicalNLP workshop. Although a straightforward fine-tuning of GPT shows promising results on the development set, it struggled with the out-of-domain questions in the test set. With our framework, we improve our system's adaptability and achieve competitive performances in the official leaderboard of the EHRSQL-2024 challenge.