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.
@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}
}