Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding

arXiv:2404.04293v1 Announce Type: new
Abstract: Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but they still struggle with some complicated reasoning tasks including logical reasoning. One non-negligible reason for LLMs' suboptimal performance on logical reasoning is their overlooking of understanding logical fallacies correctly. To evaluate LLMs' capability of logical fallacy understanding (LFU), we propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW in this paper. Towards these LFU tasks, we have successfully …

abstract arxiv cs.ai cs.cl good language language models large language large language models llms performance reason reasoning struggle tasks through type understanding