Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xi, Zhiheng, Jin, Senjie, Zhou, Yuhao, Zheng, Rui, Gao, Songyang, Gui, Tao, Zhang, Qi, Huang, Xuanjing
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913319175061504
author Xi, Zhiheng
Jin, Senjie
Zhou, Yuhao
Zheng, Rui
Gao, Songyang
Gui, Tao
Zhang, Qi
Huang, Xuanjing
author_facet Xi, Zhiheng
Jin, Senjie
Zhou, Yuhao
Zheng, Rui
Gao, Songyang
Gui, Tao
Zhang, Qi
Huang, Xuanjing
contents To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which explicitly elicits human-like rationales. However, they have inadvertently overlooked the potential of enhancing model reasoning performance by formulating higher-quality problems. In this work, we start from the problem side and propose Self-Polish (SP), a novel method that facilitates the model's reasoning by guiding it to progressively refine the given problems to be more comprehensible and solvable. We also explore several automatic prompting varients and propose the Self-Polish prompt bank for the community. SP is orthogonal to all other prompting methods of answer/reasoning side like CoT, allowing for seamless integration with state-of-the-art techniques for further improvement. Thorough experiments show that the proposed method attains notable and consistent effectiveness on five reasoning benchmarks across different models. Furthermore, our method also showcases impressive performance on robustness evaluation. Codes and prompts are available at https://github.com/WooooDyy/Self-Polish.
format Preprint
id arxiv_https___arxiv_org_abs_2305_14497
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
Xi, Zhiheng
Jin, Senjie
Zhou, Yuhao
Zheng, Rui
Gao, Songyang
Gui, Tao
Zhang, Qi
Huang, Xuanjing
Computation and Language
Artificial Intelligence
To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which explicitly elicits human-like rationales. However, they have inadvertently overlooked the potential of enhancing model reasoning performance by formulating higher-quality problems. In this work, we start from the problem side and propose Self-Polish (SP), a novel method that facilitates the model's reasoning by guiding it to progressively refine the given problems to be more comprehensible and solvable. We also explore several automatic prompting varients and propose the Self-Polish prompt bank for the community. SP is orthogonal to all other prompting methods of answer/reasoning side like CoT, allowing for seamless integration with state-of-the-art techniques for further improvement. Thorough experiments show that the proposed method attains notable and consistent effectiveness on five reasoning benchmarks across different models. Furthermore, our method also showcases impressive performance on robustness evaluation. Codes and prompts are available at https://github.com/WooooDyy/Self-Polish.
title Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2305.14497