ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback

arXiv:2404.00934v1 Announce Type: new
Abstract: ChatGLM is a free-to-use AI service powered by the ChatGLM family of large language models (LLMs). In this paper, we present the ChatGLM-RLHF pipeline -- a reinforcement learning from human feedback (RLHF) system -- designed to enhance ChatGLM's alignment with human preferences. ChatGLM-RLHF encompasses three major components: the collection of human preference data, the training of the reward model, and the optimization of policies. Throughout the process of integrating ChatGLM-RLHF into production, we encountered and …

abstract alignment arxiv cs.cl family feedback free human human feedback language language models large language large language models llms paper pipeline practices reinforcement reinforcement learning rlhf service type