Saved in:
Bibliographic Details
Main Authors: Sun, Haoran, Zhang, Zekun, Zeng, Shaoning
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.15281
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915401658531840
author Sun, Haoran
Zhang, Zekun
Zeng, Shaoning
author_facet Sun, Haoran
Zhang, Zekun
Zeng, Shaoning
contents The capabilities of Large Language Models (LLMs) are limited to some extent by pre-training, so some researchers optimize LLMs through post-training. Existing post-training strategies, such as memory-based retrieval or preference optimization, improve user alignment yet fail to enhance the model's domain cognition. To bridge this gap, we propose a novel Dual-Phase Self-Evolution (DPSE) framework that jointly optimizes user preference adaptation and domain-specific competence. DPSE introduces a Censor module to extract multi-dimensional interaction signals and estimate satisfaction scores, which guide structured data expansion via topic-aware and preference-driven strategies. These expanded datasets support a two-stage fine-tuning pipeline: supervised domain grounding followed by frequency-aware preference optimization. Experiments across general NLP benchmarks and long-term dialogue tasks demonstrate that DPSE consistently outperforms Supervised Fine-Tuning, Preference Optimization, and Memory-Augmented baselines. Ablation studies validate the contribution of each module. In this way, our framework provides an autonomous path toward continual self-evolution of LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15281
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Novel Self-Evolution Framework for Large Language Models
Sun, Haoran
Zhang, Zekun
Zeng, Shaoning
Computation and Language
Artificial Intelligence
The capabilities of Large Language Models (LLMs) are limited to some extent by pre-training, so some researchers optimize LLMs through post-training. Existing post-training strategies, such as memory-based retrieval or preference optimization, improve user alignment yet fail to enhance the model's domain cognition. To bridge this gap, we propose a novel Dual-Phase Self-Evolution (DPSE) framework that jointly optimizes user preference adaptation and domain-specific competence. DPSE introduces a Censor module to extract multi-dimensional interaction signals and estimate satisfaction scores, which guide structured data expansion via topic-aware and preference-driven strategies. These expanded datasets support a two-stage fine-tuning pipeline: supervised domain grounding followed by frequency-aware preference optimization. Experiments across general NLP benchmarks and long-term dialogue tasks demonstrate that DPSE consistently outperforms Supervised Fine-Tuning, Preference Optimization, and Memory-Augmented baselines. Ablation studies validate the contribution of each module. In this way, our framework provides an autonomous path toward continual self-evolution of LLMs.
title A Novel Self-Evolution Framework for Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.15281