1. LP-LM: No Hallucinations in Question Answering with Logic Programming
- Author
-
Wu, Katherine and Liu, Yanhong A.
- Subjects
Computer Science - Artificial Intelligence ,Computer Science - Computation and Language - Abstract
Large language models (LLMs) are able to generate human-like responses to user queries. However, LLMs exhibit inherent limitations, especially because they hallucinate. This paper introduces LP-LM, a system that grounds answers to questions in known facts contained in a knowledge base (KB), facilitated through semantic parsing in Prolog, and always produces answers that are reliable. LP-LM generates a most probable constituency parse tree along with a corresponding Prolog term for an input question via Prolog definite clause grammar (DCG) parsing. The term is then executed against a KB of natural language sentences also represented as Prolog terms for question answering. By leveraging DCG and tabling, LP-LM runs in linear time in the size of input sentences for sufficiently many grammar rules. Performing experiments comparing LP-LM with current well-known LLMs in accuracy, we show that LLMs hallucinate on even simple questions, unlike LP-LM., Comment: In Proceedings ICLP 2024, arXiv:2502.08453
- Published
- 2025
- Full Text
- View/download PDF