GRAM: A Generative Foundation Reward Model for Reward Generalization

• URL: http://arxiv.org/abs/2506.14175v2
• Date: Wed, 18 Jun 2025 04:31:51 GMT
• Title: GRAM: A Generative Foundation Reward Model for Reward Generalization
• Authors: Chenglong Wang, Yang Gan, Yifu Huo, Yongyu Mu, Qiaozhi He, Murun Yang, Bei Li, Tong Xiao, Chunliang Zhang, Tongran Liu, Jingbo Zhu,
• Abstract summary: We develop a generative reward model that is first trained via large-scale unsupervised learning and then fine-tuned via supervised learning.<n>This model generalizes well across several tasks, including response ranking, reinforcement learning from human feedback, and task adaptation with fine-tuning.
• Score: 48.63394690265176
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In aligning large language models (LLMs), reward models have played an important role, but are standardly trained as discriminative models and rely only on labeled human preference data. In this paper, we explore methods that train reward models using both unlabeled and labeled data. Building on the generative models in LLMs, we develop a generative reward model that is first trained via large-scale unsupervised learning and then fine-tuned via supervised learning. We also show that by using label smoothing, we are in fact optimizing a regularized pairwise ranking loss. This result, in turn, provides a new view of training reward models, which links generative models and discriminative models under the same class of training objectives. The outcome of these techniques is a foundation reward model, which can be applied to a wide range of tasks with little or no further fine-tuning effort. Extensive experiments show that this model generalizes well across several tasks, including response ranking, reinforcement learning from human feedback, and task adaptation with fine-tuning, achieving significant performance improvements over several strong baseline models.

Related papers

• Activation Reward Models for Few-Shot Model Alignment [77.37511364793515]
  We introduce Activation Reward Models (Activation RMs)<n>Activation RMs leverage activation steering to construct well-aligned reward signals using minimal supervision and no additional model finetuning.<n>We demonstrate the effectiveness of Activation RMs in mitigating reward hacking behaviors, highlighting their utility for safety-critical applications.
  arXiv  Detail & Related papers  (2025-07-02T05:10:29Z)
• Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
  Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data. We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
  arXiv  Detail & Related papers  (2024-10-22T06:43:28Z)
• EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models [36.576853882830896]
  We introduce EvolveDirector to train a text-to-image generation model comparable to advanced models using publicly available resources. This framework interacts with advanced models through their public APIs to obtain text-image data pairs to train a base model. We leverage pre-trained large vision-language models (VLMs) to guide the evolution of the base model.
  arXiv  Detail & Related papers  (2024-10-09T17:52:28Z)
• A Two-Phase Recall-and-Select Framework for Fast Model Selection [13.385915962994806]
  We propose a two-phase (coarse-recall and fine-selection) model selection framework. It aims to enhance the efficiency of selecting a robust model by leveraging the models' training performances on benchmark datasets. It has been demonstrated that the proposed methodology facilitates the selection of a high-performing model at a rate about 3x times faster than conventional baseline methods.
  arXiv  Detail & Related papers  (2024-03-28T14:44:44Z)
• RewardBench: Evaluating Reward Models for Language Modeling [100.28366840977966]
  We present RewardBench, a benchmark dataset and code-base for evaluation of reward models. The dataset is a collection of prompt-chosen-rejected trios spanning chat, reasoning, and safety. On the RewardBench leaderboard, we evaluate reward models trained with a variety of methods.
  arXiv  Detail & Related papers  (2024-03-20T17:49:54Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
  We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset. We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
  arXiv  Detail & Related papers  (2024-01-11T17:56:59Z)
• Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models [11.57282859281814]
  We consider different knowledge levels and attribution strategies, and find that we can correctly trace back 8 out of the 10 fine tuned models with our best method.
  arXiv  Detail & Related papers  (2023-06-15T17:42:48Z)
• RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment [32.752633250862694]
  Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. We introduce a new framework, Reward rAnked FineTuning, designed to align generative models effectively.
  arXiv  Detail & Related papers  (2023-04-13T18:22:40Z)
• Revealing Secrets From Pre-trained Models [2.0249686991196123]
  Transfer-learning has been widely adopted in many emerging deep learning algorithms. We show that pre-trained models and fine-tuned models have significantly high similarities in weight values. We propose a new model extraction attack that reveals the model architecture and the pre-trained model used by the black-box victim model.
  arXiv  Detail & Related papers  (2022-07-19T20:19:03Z)

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.