English

Using Language Models For Knowledge Acquisition in Natural Language Reasoning Problems

Artificial Intelligence 2023-04-05 v1

Abstract

For a natural language problem that requires some non-trivial reasoning to solve, there are at least two ways to do it using a large language model (LLM). One is to ask it to solve it directly. The other is to use it to extract the facts from the problem text and then use a theorem prover to solve it. In this note, we compare the two methods using ChatGPT and GPT4 on a series of logic word puzzles, and conclude that the latter is the right approach.

Keywords

Cite

@article{arxiv.2304.01771,
  title  = {Using Language Models For Knowledge Acquisition in Natural Language Reasoning Problems},
  author = {Fangzhen Lin and Ziyi Shou and Chengcai Chen},
  journal= {arXiv preprint arXiv:2304.01771},
  year   = {2023}
}
R2 v1 2026-06-28T09:48:58.686Z