KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR

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 Figure 1: In the proposed Text-to-SQL framework, workshop. Although a straightforward finetuning when a query is presented in natural language, the model of GPT shows promising results on the generates SQL code to retrieve the required information development set, it struggled with the out-ofdomain from the database. If the query requires information absent questions in the test set. With our from the database, the Text-to-SQL model returns framework, we improve our system's adaptability a'null' response.