paper-with-me

Papers

Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment

2024-05-31 · Yueqin Yin, Zhendong Wang, Yujia Xie, Weizhu Chen, Mingyuan Zhou

Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability. To overcome this limitation, we introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation. Specifically, we employ an Exponential Moving Average (EMA) model in conjunction with a replay buffer to enable dynamic updates of response segments, effectively integrating real-time feedback with insights from historical data. Our comprehensive evaluations of the LLaMA3-8B and Mistral-7B models across benchmarks, including the Open LLM Leaderboard, IFEval, AlpacaEval 2.0, and MT-Bench, demonstrate that SAPO matches or surpasses established offline contrastive baselines, such as DPO and Odds Ratio Preference Optimization, and outperforms offline self-play methods like SPIN. Our code is available at https://github.com/yinyueqin/SAPO

📄 PDF Abstract BibTeX arXiv:2405.20830

Code (1)

yinyueqin/sapo 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

DPO 설명 없음

Similar Papers 제목 키워드 기반

Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization

2024-09-17 · Jianing Wang, Yang Zhou, Xiaocheng Zhang, Mengjiao Bao 외

Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in t…

Policy Teaching via Data Poisoning in Learning from Human Preferences

2025-03-13 · Andi Nika, Jonathan Nöther, Debmalya Mandal, Parameswaran Kamalaruban 외

We study data poisoning attacks in learning from human preferences. More specifically, we consider the problem of teaching/enforcing a target policy $\pi^\dagger$ by synthesizing preference data. We seek to understand th…

Data Poisoning

SGPO: Self-Generated Preference Optimization based on Self-Improver

2025-07-27 · Hyeonji Lee, Daejin Jo, Seohwan Yun, Sungwoong Kim arxiv

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically empl…

Aligning Large Language Models by On-Policy Self-Judgment

2024-02-17 · Sangkyu Lee, Sungdong Kim, Ashkan Yousefpour, Minjoon Seo 외

Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we present a novel alignment framework, SEL…

Instruction Following

Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences

2024-03-04 · Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, Georgios Tzannetos 외

In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedback (RLHF) with the recently proposed par…