SPARQL Query Generation Using LLMs for Medical Information Retrieval

Charalampos Doulaverakis, Giannis Vassiliou, Sotiris Batsakis, Nikos Papadakis, Georgia Eirini Trouli, Grigoris Antoniou

Abstract: Large Language Models (LLMs) have been the focus of Artificial Intelligence (AI) research recently but evaluation of their performance demonstrated their limitations in various tasks requiring reasoning capabilities. Responses of LLMs often contain erroneous answers and non existent facts, which is a major problem especially in critical tasks such as medical applications. In this work we propose a solution to this problem by making use of Linked Open Data as a source of reliable information. Specifically, we propose an approach that leverages Large Language Models (LLM) in order to allow for automatic SPARQL query generation from natural language by providing example entries of the dataset to the LLM so that it can analyze its structure. Preliminary results demonstrate the potential of our approach, and we provide an online demo so that users can experiment.

External IDs:dblp:conf/esws/DoulaverakisVBPTA25