The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues for LLMs and complex tasks. Our proposed framework Proto-RM leverages prototypical networks to enhance reward models under limited human feedback. By enabling stable and reliable structural learning from fewer samples, Proto-RM significantly enhances LLMs' adaptability and accuracy in interpreting human preferences. Extensive experiments on various datasets demonstrate that Proto-RM significantly improves the performance of reward models and LLMs in human feedback tasks, achieving comparable and usually better results than traditional methods, while requiring significantly less data. in data-limited scenarios. This research offers a promising direction for enhancing the efficiency of reward models and optimizing the fine-tuning of language models under restricted feedback conditions.
@article{arxiv.2406.06606,
title = {Prototypical Reward Network for Data-Efficient RLHF},
author = {Jinghan Zhang and Xiting Wang and Yiqiao Jin and Changyu Chen and Xinhao Zhang and Kunpeng Liu},
journal= {arXiv preprint arXiv:2406.06606},
year = {2024}
}