Few-Shot Learning or RAG in LLM-Based Text-to-SPARQL? Why Not Both?
Caio Viktor S. Avila, Vânia Maria Ponte Vidal, Wellington Franco, Marco A. Casanova · 2025
This paper introduces a hybrid approach for the text-to-SPARQL task involving Large Language Models (LLMs) by integrating Retrieval-Augmented Generation (RAG) with fewshot learning techniques. The approach enhances the AutoKGQA framework by incorporating query examples into the LLM while selecting minimal knowledge graph (KG) subgraphs as context, thereby improving its ability to interpret and answer natural language queries. Experimental results on the SciQA benchmark indicate that this integration increased the F1-score by 0.16. Notably, the framework excelled in the zero-shot setting with an F1-score of 0.73, significantly outperforming the prior score of 0.26. Additionally, the paper introduces an automated procedure to extract a minimal T-Box from KGs lacking an explicit schema, optimizing query processing by limiting deep neighborhood exploration. These findings suggest that combining KG context with query examples is an effective strategy, particularly for developing generalizable systems.