Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914965857763328 |
|---|---|
| author | Zhang, Yongheng Chen, Qiguang Zhou, Jingxuan Wang, Peng Si, Jiasheng Wang, Jin Lu, Wenpeng Qin, Libo |
| author_facet | Zhang, Yongheng Chen, Qiguang Zhou, Jingxuan Wang, Peng Si, Jiasheng Wang, Jin Lu, Wenpeng Qin, Libo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04463 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information Zhang, Yongheng Chen, Qiguang Zhou, Jingxuan Wang, Peng Si, Jiasheng Wang, Jin Lu, Wenpeng Qin, Libo Computation and Language 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. |
| title | Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.04463 |