all AI news
Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
April 17, 2024, 4:46 a.m. | Shusheng Xu, Wei Fu, Jiaxuan Gao, Wenjie Ye, Weilin Liu, Zhiyu Mei, Guangju Wang, Chao Yu, Yi Wu
cs.CL updates on arXiv.org arxiv.org
Abstract: Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free. Novel applications such as ChatGPT and Claude leverage reward-based methods that first learn a reward model and apply actor-critic algorithms, such as Proximal Policy Optimization (PPO). However, in academic benchmarks, state-of-the-art results are often achieved via reward-free methods, such as Direct …
abstract alignment applications arxiv chatgpt claude cs.cl feedback free human human feedback language language models large language large language models llm llms novel ppo reinforcement reinforcement learning rlhf study type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Engineer - AWS
@ 3Pillar Global | Costa Rica
Cost Controller/ Data Analyst - India
@ John Cockerill | Mumbai, India, India, India