LP-LM: No Hallucinations in Question Answering with Logic Programming
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915149717176320 |
|---|---|
| author | Wu, Katherine Liu, Yanhong A. |
| author_facet | Wu, Katherine Liu, Yanhong A. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09212 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LP-LM: No Hallucinations in Question Answering with Logic Programming Wu, Katherine Liu, Yanhong A. Artificial Intelligence Computation and Language 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. |
| title | LP-LM: No Hallucinations in Question Answering with Logic Programming |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2502.09212 |