While recent advances have boosted LM proficiency in linguistic benchmarks, LMs consistently struggle to reason correctly on complex tasks like mathematics. We turn to Reinforcement Learning from Human Feedback (RLHF) as a method with which to shape model reasoning processes. In particular, we explore two reward schemes, outcome-supervised reward models (ORMs) and process-supervised reward models (PRMs), to optimize for logical reasoning. Our results show that the fine-grained reward provided by PRM-based methods enhances accuracy on simple mathematical reasoning (GSM8K) while, unexpectedly, reducing performance in complex tasks (MATH). Furthermore, we show the critical role reward aggregation functions play in model performance. Providing promising avenues for future research, our study underscores the need for further exploration into fine-grained reward modeling for more reliable language models.
@article{arxiv.2311.05821,
title = {Let's Reinforce Step by Step},
author = {Sarah Pan and Vladislav Lialin and Sherin Muckatira and Anna Rumshisky},
journal= {arXiv preprint arXiv:2311.05821},
year = {2023}
}
Comments
NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following