GRISP: Guided Recurrent IRI Selection over SPARQL Skeletons
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908988026650624 |
|---|---|
| author | Walter, Sebastian Bast, Hannah |
| author_facet | Walter, Sebastian Bast, Hannah |
| contents | We present GRISP (Guided Recurrent IRI Selection over SPARQL Skeletons), a novel SPARQL-based question-answering method over knowledge graphs based on fine-tuning a small language model (SLM). Given a natural-language question, the method first uses the SLM to generate a natural-language SPARQL query skeleton, and then to re-rank and select knowledge graph items to iteratively replace the natural-language placeholders using knowledge graph constraints. The SLM is jointly trained on skeleton generation and list-wise re-ranking data generated from standard question-query pairs. We evaluate the method on common Wikidata and Freebase benchmarks, and achieve better results than other state-of-the-art methods in a comparable setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21133 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GRISP: Guided Recurrent IRI Selection over SPARQL Skeletons Walter, Sebastian Bast, Hannah Computation and Language We present GRISP (Guided Recurrent IRI Selection over SPARQL Skeletons), a novel SPARQL-based question-answering method over knowledge graphs based on fine-tuning a small language model (SLM). Given a natural-language question, the method first uses the SLM to generate a natural-language SPARQL query skeleton, and then to re-rank and select knowledge graph items to iteratively replace the natural-language placeholders using knowledge graph constraints. The SLM is jointly trained on skeleton generation and list-wise re-ranking data generated from standard question-query pairs. We evaluate the method on common Wikidata and Freebase benchmarks, and achieve better results than other state-of-the-art methods in a comparable setting. |
| title | GRISP: Guided Recurrent IRI Selection over SPARQL Skeletons |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.21133 |