paper-with-me

Papers

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint

2023-12-18 · Wei Xiong, Hanze Dong, Chenlu Ye, Ziqi Wang, Han Zhong, Heng Ji, Nan Jiang, Tong Zhang

This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in strategical exploration of the environment. Then, to understand the mathematical principle of RLHF, we consider a standard mathematical formulation, the reverse-KL regularized contextual bandit for RLHF. Despite its widespread practical application, a rigorous theoretical analysis of this formulation remains open. We investigate its behavior in three distinct settings -- offline, online, and hybrid -- and propose efficient algorithms with finite-sample theoretical guarantees. Moving towards practical applications, our framework, with a robust approximation of the information-theoretical policy improvement oracle, naturally gives rise to several novel RLHF algorithms. This includes an iterative version of the Direct Preference Optimization (DPO) algorithm for online settings, and a multi-step rejection sampling strategy for offline scenarios. Our empirical evaluations on real-world alignment experiment of large language model demonstrate that these proposed methods significantly surpass existing strong baselines, such as DPO and Rejection Sampling Optimization (RSO), showcasing the connections between solid theoretical foundations and their potent practical implementations.

📄 PDF Abstract BibTeX arXiv:2312.11456

Code (3)

RLHFlow/RLHF-Reward-Modeling pytorch
rlhflow/online-rlhf pytorch
weixiongust/rlhf-reward-modeling pytorch

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

DPO 설명 없음
Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Similar Papers 제목 키워드 기반

Self-Play Preference Optimization for Language Model Alignment

2024-05-01 · Yue Wu, Zhiqing Sun, Huizhuo Yuan, Kaixuan Ji 외

Standard reinforcement learning from human feedback (RLHF) approaches relying on parametric models like the Bradley-Terry model fall short in capturing the intransitivity and irrationality in human preferences. Recent ad…

Language ModelingLanguage Modellingmodel

Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney

2023-11-20 · Shachar Don-Yehiya, Leshem Choshen, Omri Abend

Generating images with a Text-to-Image model often requires multiple trials, where human users iteratively update their prompt based on feedback, namely the output image. Taking inspiration from cognitive work on referen…

PILAF: Optimal Human Preference Sampling for Reward Modeling

2025-02-06 · Yunzhen Feng, Ariel Kwiatkowski, Kunhao Zheng, Julia Kempe 외

As large language models increasingly drive real-world applications, aligning them with human values becomes paramount. Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique, translating prefer…

Active Learning for Direct Preference Optimization

2025-03-03 · Branislav Kveton, Xintong Li, Julian McAuley, Ryan Rossi 외

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the cr…

Active Learning

Mapping Social Choice Theory to RLHF

2024-04-19 · Jessica Dai, Eve Fleisig

Recent work on the limitations of using reinforcement learning from human feedback (RLHF) to incorporate human preferences into model behavior often raises social choice theory as a reference point. Social choice theory'…

reinforcement-learning