WeChat Mini Program
Old Version Features

Evolving LLMs' Self-Refinement Capability Via Iterative Preference Optimization

Yongcheng Zeng, Xinyu Cui, Xuanfa Jin, Guoqing Liu, Zexu Sun,Dong Li, Ning Yang,Jianye Hao,Haifeng Zhang,Jun Wang

CoRR(2025)

Cited 0|Views14
Abstract
While large language models (LLMs) have demonstrated remarkable general performance, enabling smaller models to achieve capabilities comparable to their larger counterparts remains a critical challenge. For humans, iterative refinement of problem analysis and responses is a common strategy to enhance answer quality. However, we observe that existing LLMs exhibit limited ability to refine their outputs for quality improvement. In this paper, we first investigate mechanisms to unlock and progressively enhance self-refinement ability in smaller models within an iterative preference optimization framework, aiming to bridge the performance gap with larger models. To this end, we propose EVOLVE, a novel post-training and inference framework that iteratively integrates preference training with self-refinement-driven data collection. During training, EVOLVE strengthens the model's direct question-answering ability while simultaneously unlocking its self-refinement potential. At inference, the framework leverages this capability to generate progressively refined responses, which are filtered to construct datasets for subsequent rounds of preference training. Experiments demonstrate EVOLVE's exceptional performance: when applied to Llama-3.1-8B base model and under the self-refinement setting, it surpasses state-of-the-art models including Llama-3.1-405B-Instruct and GPT-4o, achieving a 62.3 rate and 63.3 Arena-Hard. Furthermore, EVOLVE consistently enhances performance on mathematical reasoning tasks like GSM8K and MATH.
More
Translated text
PDF
Bibtex
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined