Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
Li, Yanda, Wang, Dixuan, Liang, Jiaqing, Jiang, Guochao, He, Qianyu, Xiao, Yanghua, Yang, Deqing
–arXiv.org Artificial Intelligence
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 constructed a new dataset LFUD based on GPT-4 accompanied by a little human effort. Our extensive experiments justify that our LFUD can be used not only to evaluate LLMs' LFU capability, but also to fine-tune LLMs to obtain significantly enhanced performance on logical reasoning.
arXiv.org Artificial Intelligence
Apr-4-2024
- Country:
- South America > Chile
- North America > United States
- Washington > King County
- Seattle (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Washington > King County
- Europe
- United Kingdom > England
- Greater London > London (0.04)
- Cambridgeshire > Cambridge (0.04)
- Spain > Valencian Community
- Valencia Province > Valencia (0.04)
- United Kingdom > England
- Asia
- Middle East
- Jordan (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- China
- Shanghai > Shanghai (0.04)
- Guangxi Province > Nanning (0.04)
- Middle East
- Genre:
- Research Report > New Finding (0.68)
- Technology: