A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future
By: Jialun Zhong , Wei Shen , Yanzeng Li and more
Potential Business Impact:
Teaches computers to act how people want.
Reward Model (RM) has demonstrated impressive potential for enhancing Large Language Models (LLM), as RM can serve as a proxy for human preferences, providing signals to guide LLMs' behavior in various tasks. In this paper, we provide a comprehensive overview of relevant research, exploring RMs from the perspectives of preference collection, reward modeling, and usage. Next, we introduce the applications of RMs and discuss the benchmarks for evaluation. Furthermore, we conduct an in-depth analysis of the challenges existing in the field and dive into the potential research directions. This paper is dedicated to providing beginners with a comprehensive introduction to RMs and facilitating future studies. The resources are publicly available at github\footnote{https://github.com/JLZhong23/awesome-reward-models}.
Similar Papers
Reward Model Perspectives: Whose Opinions Do Reward Models Reward?
Computation and Language
Makes AI less biased and fairer to everyone.
A Survey on Progress in LLM Alignment from the Perspective of Reward Design
Computation and Language
Teaches AI to act like good people.
Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
Computation and Language
Teaches computers to think and follow instructions better.