ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities

2025-10-02

AI Summary

Non-computer-science users struggle to translate natural language questions into executable SPARQL queries for interactive knowledge graph (KG) exploration. Method: This paper proposes a progressive Text2SPARQL approach grounded in the ReAct framework and inspired by SPINACH, integrating multi-step KG exploration with large language model (LLM)-driven iterative reasoning. The method instantiates an intelligent agent capable of executing SPARQL queries, receiving execution feedback, and performing self-correction—augmented by a SPARQL engine and an interpretable KG exploration toolkit. Contribution/Results: The approach significantly improves semantic parsing accuracy and process transparency for complex questions. Evaluated on the Text2SPARQL Challenge benchmark, it achieves substantially higher query accuracy than state-of-the-art baselines. Behavioral analysis further identifies recurring error patterns, providing empirical grounding for future refinements.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Question Answering
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

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.

Problem

• Lowering SPARQL query barrier using LLMs
• Iterative natural language to SPARQL translation
• Improving Text2SPARQL through exploration and execution

Innovation

• LLM-based iterative natural language to SPARQL translation
• ReAct framework with knowledge graph exploration utilities
• Multi-step query generation through exploration and execution