Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929760578306048 |
|---|---|
| author | Wang, Zezhong Zeng, Xingshan Liu, Weiwen Wang, Yufei Li, Liangyou Wang, Yasheng Shang, Lifeng Jiang, Xin Liu, Qun Wong, Kam-Fai |
| author_facet | Wang, Zezhong Zeng, Xingshan Liu, Weiwen Wang, Yufei Li, Liangyou Wang, Yasheng Shang, Lifeng Jiang, Xin Liu, Qun Wong, Kam-Fai |
| contents | Current research found the issue of Early Answering in large language models (LLMs), where the models already have an answer before generating the Chain-of-Thought (CoT). This phenomenon suggests a potential lack of necessary dependency between the predicted answer and the reasoning process. Consequently, two important questions arise: (1) Is CoT still necessary if the model already has an answer? (2) Can the correctness of the answer serve as valid evidence for the correctness of CoT? To address these questions, we propose a method, namely Chain-of-Probe (CoP), to probe changes in the mind during the model's reasoning. The probing results show that in a significant number of question-answer cases, CoT appears to be unnecessary, and this necessity correlates with the simplicity of the task, defined by reasoning steps required. Furthermore, by analyzing patterns in mind change, we examine the correctness of the model's reasoning. Our validation reveals that many responses, although correct in their final answer, contain errors in their reasoning process. To this end, we propose a strategic approach based on CoP to prioritize answers with correct reasoning among multiple candidates, thereby bolstering the reliability of the model's reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16144 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step Wang, Zezhong Zeng, Xingshan Liu, Weiwen Wang, Yufei Li, Liangyou Wang, Yasheng Shang, Lifeng Jiang, Xin Liu, Qun Wong, Kam-Fai Computation and Language Current research found the issue of Early Answering in large language models (LLMs), where the models already have an answer before generating the Chain-of-Thought (CoT). This phenomenon suggests a potential lack of necessary dependency between the predicted answer and the reasoning process. Consequently, two important questions arise: (1) Is CoT still necessary if the model already has an answer? (2) Can the correctness of the answer serve as valid evidence for the correctness of CoT? To address these questions, we propose a method, namely Chain-of-Probe (CoP), to probe changes in the mind during the model's reasoning. The probing results show that in a significant number of question-answer cases, CoT appears to be unnecessary, and this necessity correlates with the simplicity of the task, defined by reasoning steps required. Furthermore, by analyzing patterns in mind change, we examine the correctness of the model's reasoning. Our validation reveals that many responses, although correct in their final answer, contain errors in their reasoning process. To this end, we propose a strategic approach based on CoP to prioritize answers with correct reasoning among multiple candidates, thereby bolstering the reliability of the model's reasoning. |
| title | Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.16144 |