Year: 2026
Type: preprint
Abstract: We present GRISP (Guided Recurrent IRI Selection over SPARQL Skeletons), a novel SPARQL-based question-answering method over knowledge graphs using a fine-tuned small language model (SLM). Given a natural-language question, the method uses the SLM to generate a natural-language SPARQL query skeleton, and then resolves the natural-language placeholders using a backtracking search that retrieves and re-ranks knowledge graph items under knowledge graph constraints. The SLM is jointly trained on skeleton generation and re-ranking data generated from question-query pairs. We evaluate the method on common Wikidata and Freebase benchmarks, and achieve better results than other state-of-the-art fine-tuning-based methods.
Source: arXiv (Cornell University)
Authors: Walter, Sebastian, Bast, Hannah
Institution: University of Freiburg
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Deutsche Forschungsgemeinschaft
Awards: G3547540627, SFB 1597: Small Data
OpenAlex ID: W7155494983