Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information

Yongheng Zhang, Qiguang Chen, Jingxuan Zhou, Peng Wang, Jiasheng Si, Jin Wang, Wenpeng Lu, Libo Qin


Abstract
Chain-of-Thought (CoT) has become a vital technique for enhancing the performance of Large Language Models (LLMs), attracting increasing attention from researchers. One stream of approaches focuses on the iterative enhancement of LLMs by continuously verifying and refining their reasoning outputs for desired quality. Despite its impressive results, this paradigm faces two critical issues: (1) Simple verification methods: The current paradigm relies solely on a single verification method. (2) Wrong Information Ignorance: Traditional paradigms directly ignore wrong information during reasoning and refine the logic paths from scratch each time. To address these challenges, we propose Wrong-of-Thought (WoT), which includes two core modules: (1) Multi-Perspective Verification: A multi-perspective verification method for accurately refining the reasoning process and result, and (2) Wrong Information Utilization: Utilizing wrong information to alert LLMs and reduce the probability of LLMs making same mistakes. Experiments on 8 popular datasets and 5 LLMs demonstrate that WoT surpasses all previous baselines. In addition, WoT exhibits powerful capabilities in difficult computation tasks.
Anthology ID:
2024.findings-emnlp.388
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6644–6653
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.388
DOI:
Bibkey:
Cite (ACL):
Yongheng Zhang, Qiguang Chen, Jingxuan Zhou, Peng Wang, Jiasheng Si, Jin Wang, Wenpeng Lu, and Libo Qin. 2024. Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6644–6653, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information (Zhang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.388.pdf