Logo image
Improving the Accuracy of Black-Box Language Models with Ontologies: A Preliminary Roadmap
Conference proceeding   Open access   Peer reviewed

Improving the Accuracy of Black-Box Language Models with Ontologies: A Preliminary Roadmap

Proceedings of the Joint Ontology Workshops (JOWO) - Episode X: The Tukker Zomer of Ontology, and satellite events co-located with the 14th International Conference on Formal Ontology in Information Systems (FOIS 2024), Enschede, The Netherlands, July 15-19, 2024, Vol.3882, pp.1-10
CEUR Workshop Proceedings, 3882
2024 Joint Ontology Workshops - Episode X: The Tukker Zomer of Ontology, and Satellite Events, JOWO 2024 (Enschede, 15/07/2024–19/07/2024)
2024
Handle:
https://hdl.handle.net/10863/51581

Abstract

Large Language Models (LLMs) Ontologies Neuro-symbolic reasoning
Large Language Models (LLMs) have revolutionised natural language generation. But their statistical and auto-regressive nature makes them unreliable. It has become clear to the research community that in order to produce reliably correct answers, LLMs need to be enriched in some way with ‘world models’ reflecting the semantics of the domains being queried. We here propose a simple workflow to address this problem through a neuro-symbolic interaction protocol with the LLM treated as a blackbox. Answers given by an LLM are checked against accepted knowledge provided by a domain ontology. The approach aims to combine conflict detection with explanation extraction and formal repairs presented to the LLM in the form of specific artificial speech acts. The goal is to build constraining, incremental prompts that improve repeatability and veracity in the LLM’s output.
pdf
llm-14.67 MBDownloadView
Open Access
url
https://ceur-ws.org/Vol-3882/llm-1.pdfView

Details

Metrics

1 Record Views
Logo image