Communication Dans Un Congrès Année : 2025

Instruct-to-SPARQL: A text-to-SPARQL dataset for training Wikidata Agents

Résumé

The rapid adoption of Large Language Models (LLMs) for search engines and fact-checking platforms necessitates enhancing their output accuracy. Retrieval Augmented Generation (RAG) mitigates hallucinations but requires semantically rich repositories like Wikidata. However, there is a lack of high-quality data to fine-tune LLMs for querying such knowledge bases. To address this gap, we propose a curated dataset with 2,771 unique queries for fine-tuning LLMs to generate accurate and syntactically valid SPARQL queries from natural language instructions. This dataset, customized for interaction with Wikidata, also serves as a robust benchmark for text-to-SPARQL task evaluation. Key findings show that models generally perform better on queries with lower complexity.
Fichier principal
Vignette du fichier
CHIIR_25_SPARQL_LLM.pdf (478) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04918564 , version 1 (29-01-2025)

Identifiants

Citer

Alexis Strappazon, Michael Granitzer, Előd Egyed-Zsigmond, Jelena Mitrovic, Mehdi Ben Amor. Instruct-to-SPARQL: A text-to-SPARQL dataset for training Wikidata Agents. ACM SIGIR Conference on Human Information Interaction And Retrieval, ACM, Mar 2025, Melbourne (AUS), Australia. ⟨10.1145/nnnnnnn.nnnnnnn⟩. ⟨hal-04918564⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More