Inference-Time Scaling for Generalist Reward Modeling
- URL: http://arxiv.org/abs/2504.02495v2
- Date: Sat, 05 Apr 2025 17:04:00 GMT
- Title: Inference-Time Scaling for Generalist Reward Modeling
- Authors: Zijun Liu, Peiyi Wang, Runxin Xu, Shirong Ma, Chong Ruan, Peng Li, Yang Liu, Yu Wu,
- Abstract summary: Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale.<n>Key challenge of RL is to obtain accurate reward signals for LLMs in various domains beyond verifiable questions or artificial rules.<n>In this work, we investigate how to improve reward modeling with more inference compute for general queries.
- Score: 25.62000059973935
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: 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 $\textit{proper learning methods could enable effective inference-time scalability}$. 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 $\textbf{inference-time scalability of generalist RM}$, 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 $\textbf{DeepSeek-GRM}$ 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.
Related papers
- Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner [31.033131727230277]
Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL)<n>We propose a novel intrinsic signal-driven generative process evaluation mechanism operating at the thought level to address major bottlenecks in RL-based training.<n>Experiments on 1.5B and 7B parameter LRMs demonstrate that our method achieves higher problem-solving accuracy with significantly fewer training samples than outcome-only reward baselines.
arXiv Detail & Related papers (2025-07-31T07:54:58Z) - Discriminative Policy Optimization for Token-Level Reward Models [55.98642069903191]
Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs)<n>Q-RM explicitly learns token-level Q-functions from preference data without relying on fine-grained annotations.<n>Reinforcement learning with Q-RM significantly enhances training efficiency, achieving convergence 12 times faster than ORM on GSM8K and 11 times faster than step-level PRM on MATH.
arXiv Detail & Related papers (2025-05-29T11:40:34Z) - From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling [32.72867198629561]
We investigate the interplay between pre-training and reward model training FLOPs to assess their influence on PRM efficiency and accuracy.<n>Our findings indicate that PRMs trained on mathematical datasets exhibit performance comparable to those tailored for code generation.
arXiv Detail & Related papers (2025-05-24T12:44:15Z) - Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models [50.4652276723694]
Think-RM generates flexible, self-guided reasoning traces that support advanced capabilities.<n>Think-RM achieves state-of-the-art results on RM-Bench, outperforming both BT RM and vertically scaled GenRM by 8%.
arXiv Detail & Related papers (2025-05-22T05:56:11Z) - Exploring Training and Inference Scaling Laws in Generative Retrieval [50.82554729023865]
We investigate how model size, training data scale, and inference-time compute jointly influence generative retrieval performance.<n>Our experiments show that n-gram-based methods demonstrate strong alignment with both training and inference scaling laws.<n>We find that LLaMA models consistently outperform T5 models, suggesting a particular advantage for larger decoder-only models in generative retrieval.
arXiv Detail & Related papers (2025-03-24T17:59:03Z) - OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
arXiv Detail & Related papers (2025-03-21T17:52:43Z) - LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
arXiv Detail & Related papers (2025-02-19T14:58:48Z) - On the Emergence of Thinking in LLMs I: Searching for the Right Intuition [34.32871896067864]
We propose a post-training framework called Reinforcement Learning via Self-Play (RLSP)
RLSP involves three steps: supervised fine-tuning with human or synthetic demonstrations of the reasoning process, using an exploration reward signal to encourage diverse and efficient reasoning behaviors, and RL training with an outcome verifier to ensure correctness while preventing reward hacking.
Empirical studies in the math domain show that RLSP improves reasoning.
arXiv Detail & Related papers (2025-02-10T18:52:04Z) - Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling [87.17041933863041]
Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs)<n>We introduce a $textbfR$esponse-$textbfc$onditioned $textbfB$radley-$textbfT$erry (Rc-BT) model that enhances the model's capability in length bias mitigating and length instruction following.<n>We also propose the Rc-RM and Rc-DPO algorithm to leverage the Rc-BT model for reward modeling and direct policy optimization
arXiv Detail & Related papers (2025-02-02T14:50:25Z) - Process Supervision-Guided Policy Optimization for Code Generation [15.943210767010045]
Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation.
We propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement.
arXiv Detail & Related papers (2024-10-23T07:22:33Z) - GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment [36.52424795446663]
Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences.<n>Test-time alignment methods address this by using reward models (RMs) to guide frozen LLMs without retraining.<n>We introduce GenARM, a test-time alignment approach that leverages the Autoregressive Reward Model.
arXiv Detail & Related papers (2024-10-10T17:58:24Z) - VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates.
We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
arXiv Detail & Related papers (2024-10-02T15:49:30Z) - Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis [16.288866201806382]
We develop a model-free RLHF best policy identification algorithm, called $mathsfBSAD$, without explicit reward model inference.<n>The algorithm identifies the optimal policy directly from human preference information in a backward manner.
arXiv Detail & Related papers (2024-06-11T17:01:41Z) - Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process.
We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals.
The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
arXiv Detail & Related papers (2024-05-01T11:10:24Z) - Let's reward step by step: Step-Level reward model as the Navigators for
Reasoning [64.27898739929734]
Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase.
We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs.
To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
arXiv Detail & Related papers (2023-10-16T05:21:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.