LP-LM: No Hallucinations in Question Answering with Logic Programming

TL;DR

LP-LM is a logic programming-based question answering system that eliminates hallucinations by grounding answers in a knowledge base, demonstrating higher reliability than traditional large language models.

Contribution

The paper introduces LP-LM, a novel system combining semantic parsing and Prolog to ensure hallucination-free, reliable question answering grounded in known facts.

Findings

LP-LM outperforms LLMs in accuracy on simple questions.

LP-LM guarantees answers are grounded in the knowledge base.

LP-LM runs in linear time for many grammar rules.

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.