Large Language Models Can Self-Correct with Key Condition Verification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929525239054336 |
|---|---|
| author | Wu, Zhenyu Zeng, Qingkai Zhang, Zhihan Tan, Zhaoxuan Shen, Chao Jiang, Meng |
| author_facet | Wu, Zhenyu Zeng, Qingkai Zhang, Zhihan Tan, Zhaoxuan Shen, Chao Jiang, Meng |
| contents | Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find that a simple yet effective verification method can unleash inherent capabilities of the LLMs. That is to mask a key condition in the question, add the current response to construct a verification question, and predict the condition to verify the response. The condition can be an entity in an open-domain question or a numeric value in a math question, which requires minimal effort (via prompting) to identify. We propose an iterative verify-then-correct framework to progressively identify and correct (probably) false responses, named ProCo. We conduct experiments on three reasoning tasks. On average, ProCo, with GPT-3.5-Turbo as the backend LLM, yields $+6.8$ exact match on four open-domain question answering datasets, $+14.1$ accuracy on three arithmetic reasoning datasets, and $+9.6$ accuracy on a commonsense reasoning dataset, compared to Self-Correct. Our implementation is made publicly available at https://wzy6642.github.io/proco.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14092 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large Language Models Can Self-Correct with Key Condition Verification Wu, Zhenyu Zeng, Qingkai Zhang, Zhihan Tan, Zhaoxuan Shen, Chao Jiang, Meng Computation and Language Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find that a simple yet effective verification method can unleash inherent capabilities of the LLMs. That is to mask a key condition in the question, add the current response to construct a verification question, and predict the condition to verify the response. The condition can be an entity in an open-domain question or a numeric value in a math question, which requires minimal effort (via prompting) to identify. We propose an iterative verify-then-correct framework to progressively identify and correct (probably) false responses, named ProCo. We conduct experiments on three reasoning tasks. On average, ProCo, with GPT-3.5-Turbo as the backend LLM, yields $+6.8$ exact match on four open-domain question answering datasets, $+14.1$ accuracy on three arithmetic reasoning datasets, and $+9.6$ accuracy on a commonsense reasoning dataset, compared to Self-Correct. Our implementation is made publicly available at https://wzy6642.github.io/proco.github.io/. |
| title | Large Language Models Can Self-Correct with Key Condition Verification |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.14092 |