paper-with-me

Papers

Does RLHF Scale? Exploring the Impacts From Data, Model, and Method

2024-12-08 · Zhenyu Hou, Pengfan Du, Yilin Niu, Zhengxiao Du, Aohan Zeng, Xiao Liu, Minlie Huang, Hongning Wang, Jie Tang, Yuxiao Dong

This study explores the scaling properties of Reinforcement Learning from Human Feedback (RLHF) in Large Language Models (LLMs). Although RLHF is considered an important step in post-training of LLMs, its scaling potential is still largely unknown. We systematically analyze key components in the RLHF framework--model size, data composition, and inference budget--and their impacts on performance. Our findings show that increasing data diversity and volume improves reward model performance, helping process-supervision models scale better. For policy training, more response samples per prompt boost performance initially but quickly plateau. And larger reward models offer modest gains in policy training. In addition, larger policy models benefit less from RLHF with a fixed reward model. Overall, RLHF scales less efficiently than pretraining, with diminishing returns from additional computational resources. Based on these observations, we propose strategies to optimize RLHF performance within computational limits.

📄 PDF Abstract BibTeX arXiv:2412.06000

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF

2023-09-16 · Simeng Sun, Dhawal Gupta, Mohit Iyyer

During the last stage of RLHF, a large language model is aligned to human intents via PPO training, a process that generally requires large-scale computational resources. In this technical report, we empirically investig…

Language ModellingLarge Language Model

Avoiding $\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration

2025-02-02 · Mingyu Chen, Yiding Chen, Wen Sun, Xuezhou Zhang

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for large language model (LLM) alignment. This paper studies the setting of online RLHF and focus on improving sample efficiency. All e…

Language ModelingLanguage ModellingLarge Language Model

Perspectives on the Social Impacts of Reinforcement Learning with Human Feedback

2023-03-06 · Gabrielle Kaili-May Liu

Is it possible for machines to think like humans? And if it is, how should we go about teaching them to do so? As early as 1950, Alan Turing stated that we ought to teach machines in the way of teaching a child. Reinforc…

Misinformationreinforcement-learningReinforcement Learning (RL)

Understanding and Alleviating Memory Consumption in RLHF for LLMs

2024-10-21 · Jin Zhou, Hanmei Yang, Steven, Tang 외

Fine-tuning with Reinforcement Learning with Human Feedback (RLHF) is essential for aligning large language models (LLMs). However, RLHF often encounters significant memory challenges. This study is the first to examine …

Managementreinforcement-learningReinforcement Learning

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

2025-03-28 · Wei Shen, Guanlin Liu, Zheng Wu, Ruofei Zhu 외

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvements, the importance of prompt-data constru…

Diversity