A Critical Evaluation of AI Feedback for Aligning Large Language Models

arXiv:2402.12366v1 Announce Type: new
Abstract: Reinforcement learning with AI feedback (RLAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. RLAIF first performs supervised fine-tuning (SFT) using demonstrations from a teacher model and then further fine-tunes the model with reinforcement learning (RL), using feedback from a critic model. While recent popular open-source models have demonstrated substantial improvements in performance from the RL step, in this paper we question whether the complexity of this RL step …

abstract arxiv cs.ai cs.cl cs.lg evaluation feedback fine-tuning language language models large language large language models paradigm popular reinforcement reinforcement learning rlaif sft supervised fine-tuning type