ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities
This work addresses the barrier of using SPARQL for non-experts by providing a generalized Text2SPARQL approach, though it appears incremental as it extends an existing method.
The paper tackles the problem of translating natural language questions to SPARQL queries for knowledge graphs by introducing ARUQULA, an LLM-based method that uses iterative exploration and execution instead of single-shot translation. It builds on SPINACH and was motivated by the Text2SPARQL challenge, with analysis conducted to identify areas for future improvements.
Interacting with knowledge graphs can be a daunting task for people without a background in computer science since the query language that is used (SPARQL) has a high barrier of entry. Large language models (LLMs) can lower that barrier by providing support in the form of Text2SPARQL translation. In this paper we introduce a generalized method based on SPINACH, an LLM backed agent that translates natural language questions to SPARQL queries not in a single shot, but as an iterative process of exploration and execution. We describe the overall architecture and reasoning behind our design decisions, and also conduct a thorough analysis of the agent behavior to gain insights into future areas for targeted improvements. This work was motivated by the Text2SPARQL challenge, a challenge that was held to facilitate improvements in the Text2SPARQL domain.