paper-with-me

홈 › Papers

Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only

2025-10-24 · Qingru Zhang, Liang Qiu, Ilgee Hong, Zhenghao Xu, Tianyi Liu, Shiyang Li, Rongzhi Zhang, Zheng Li, Lihong Li, Bing Yin, Chao Zhang, Jianshu Chen, Haoming Jiang, Tuo Zhao arxiv

Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models (LLMs) with human-annotated demonstrations. However, SFT, being an off-policy approach similar to behavior cloning, often struggles with overfitting and poor out-of-domain generalization, especially in limited-data scenarios. To address these limitations, we propose Self-Rewarding PPO, a novel fine-tuning method that leverages on-policy techniques to enhance generalization performance. Our approach combines the strengths of SFT and proximal policy optimization (PPO) to achieve more effective alignment from demonstration data. At its core is a reward function designed as the log policy ratio between the SFT model and the pretrained base model. This function serves as an implicit reward signal, using the pretrained policy as a baseline and the SFT policy as a target. By doing so, it enables on-policy fine-tuning without relying on human preference annotations. The integration of this self-rewarding mechanism with PPO addresses key limitations of SFT, improving generalization, data efficiency, and robustness. Our empirical evaluation across a range of natural language processing tasks demonstrates that Self-Rewarding PPO consistently outperforms traditional SFT methods. The results highlight the effectiveness of our approach in aligning LLMs using demonstration data, particularly in scenarios where high-quality annotated data is scarce.

📄 PDF Abstract BibTeX arXiv:2510.21090

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Generalization

Similar Papers 제목 키워드 기반

Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation

2024-02-19 · Aiwei Liu, Haoping Bai, Zhiyun Lu, Xiang Kong 외

Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the response preference by using the output pr…

Language ModelingLanguage ModellingLarge Language Model

Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models

2024-11-13 · Somanshu Singla, Zhen Wang, Tianyang Liu, Abdullah Ashfaq 외

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs…

Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models

2024-05-01 · Leonardo Ranaldi, Andrè Freitas

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although th…

Math

Process-based Self-Rewarding Language Models

2025-03-05 · Shimao Zhang, Xiao Liu, Xin Zhang, Junxiao Liu 외

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve …

Mathematical Reasoning

Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models

2025-02-13 · Xin Zhou, Yiwen Guo, Ruotian Ma, Tao Gui 외

Aligning Large Language Models (LLMs) with human preferences is crucial for their deployment in real-world applications. Recent advancements in Self-Rewarding Language Models suggest that an LLM can use its internal rewa…