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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Brei, Felix, Bühmann, Lorenz, Frey, Johannes, Gerber, Daniel, Meyer, Lars-Peter, Stadler, Claus, Bulert, Kirill
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912623566520320
author Brei, Felix
Bühmann, Lorenz
Frey, Johannes
Gerber, Daniel
Meyer, Lars-Peter
Stadler, Claus
Bulert, Kirill
author_facet Brei, Felix
Bühmann, Lorenz
Frey, Johannes
Gerber, Daniel
Meyer, Lars-Peter
Stadler, Claus
Bulert, Kirill
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities
Brei, Felix
Bühmann, Lorenz
Frey, Johannes
Gerber, Daniel
Meyer, Lars-Peter
Stadler, Claus
Bulert, Kirill
Computation and Language
Artificial Intelligence
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.
title ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.02200