Deductive Verification of LLM Generated SPARQL Queries

Alexandre Rademaker, Guilherme Lima, Sandro Rama Fiorini, Viviane Torres da Silva


Abstract
Considering the increasing applications of Large Language Models (LLMs) to many natural language tasks, this paper presents preliminary findings on developing a verification component for detecting hallucinations of an LLM that produces SPARQL queries from natural language questions. We suggest a logic-based deductive verification of the generated SPARQL query by checking if the original NL question’s deep semantic representation entails the SPARQL’s semantic representation.
Anthology ID:
2024.dlnld-1.4
Volume:
Proceedings of the Workshop on Deep Learning and Linked Data (DLnLD) @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Gilles Sérasset, Hugo Gonçalo Oliveira, Giedre Valunaite Oleskeviciene
Venues:
DLnLD | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
45–52
Language:
URL:
https://aclanthology.org/2024.dlnld-1.4
DOI:
Bibkey:
Cite (ACL):
Alexandre Rademaker, Guilherme Lima, Sandro Rama Fiorini, and Viviane Torres da Silva. 2024. Deductive Verification of LLM Generated SPARQL Queries. In Proceedings of the Workshop on Deep Learning and Linked Data (DLnLD) @ LREC-COLING 2024, pages 45–52, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Deductive Verification of LLM Generated SPARQL Queries (Rademaker et al., DLnLD-WS 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.dlnld-1.4.pdf