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

TL;DR

This paper introduces Wrong-of-Thought (WoT), a novel reasoning framework for Large Language Models that employs multi-perspective verification and wrong information utilization to improve reasoning accuracy and reduce errors.

Contribution

The paper presents a new integrated reasoning framework with multi-perspective verification and wrong information utilization, addressing limitations of existing verification methods.

Findings

WoT outperforms all previous baselines on 8 datasets and 5 LLMs.

WoT demonstrates strong capabilities in complex computation tasks.

The framework effectively reduces repeated mistakes by leveraging wrong information.

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.