Inference-Time Scaling for Generalist Reward Modeling

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from RL indicates that proper learning methods could enable effective inference-time scalability. A key challenge of RL is to obtain accurate reward signals for LLMs in various domains beyond verifiable questions or artificial rules. In this work, we investigate how to improve reward modeling (RM) with more inference compute for general queries, i.e. the inference-time scalability of generalist RM, and further, how to improve the effectiveness of performance-compute scaling with proper learning methods. For the RM approach, we adopt pointwise generative reward modeling (GRM) to enable flexibility for different input types and potential for inference-time scaling. For the learning method, we propose Self-Principled Critique Tuning (SPCT) to foster scalable reward generation behaviors in GRMs through online RL, to generate principles adaptively and critiques accurately, resulting in DeepSeek-GRM models. Furthermore, for effective inference-time scaling, we use parallel sampling to expand compute usage, and introduce a meta RM to guide voting process for better scaling performance. Empirically, we show that SPCT significantly improves the quality and scalability of GRMs, outperforming existing methods and models in various RM benchmarks without severe biases, and could achieve better performance compared to training-time scaling. DeepSeek-GRM still meets challenges in some tasks, which we believe can be addressed by future efforts in generalist reward systems. The models will be released and open-sourced.

In this work, we investigate in different approaches for RM, and found that pointwise generative reward modeling (GRM) could unify the scoring of single, paired, and multiple responses within pure language representation, overcoming challenge (1). We explored that certain principles could guide reward generation within proper criteria for GRMs, improving the quality of rewards, which inspired us that inference-time scalability of RM might be achieved by scaling the generation of high-quality principles and accurate critiques. Based on this preliminary, we propose a novel learning method, Self-Principled Critique Tuning (SPCT), to foster effective inference-time scalable behaviors in GRMs. By leveraging rule-based online RL, SPCT enables GRMs to learn to adaptively posit principles and critiques based on the input query and responses, leading to better outcome rewards in general domains (challenge (2)). We then come up with DeepSeek-GRM-27B, which is post-trained with SPCT based on Gemma-2-27B (Team, 2024). For inference-time scaling, we expand compute usage by sampling multiple times. By sampling in parallel, DeepSeek-GRM could generate different sets of principles and according critiques, and then vote for the final reward. With larger-scale sampling, DeepSeek-GRM could judge more accurately upon principles with higher diversity, and output rewards with finer granularity, which resolves challenge (3)&(4). Furthermore, We train a meta RM besides voting for better scaling performance.