Adversarial Training of Reward Models

• URL: http://arxiv.org/abs/2504.06141v2
• Date: Fri, 11 Apr 2025 18:28:40 GMT
• Title: Adversarial Training of Reward Models
• Authors: Alexander Bukharin, Haifeng Qian, Shengyang Sun, Adithya Renduchintala, Soumye Singhal, Zhilin Wang, Oleksii Kuchaiev, Olivier Delalleau, Tuo Zhao,
• Abstract summary: We introduce Adv-RM, a novel adversarial training framework that automatically identifies adversarial examples.<n>By leveraging reinforcement learning, Adv-RM trains a policy to expose vulnerabilities in large state-of-the-art reward models.<n>We demonstrate that Adv-RM significantly outperforms conventional reward training.
• Score: 74.17196154247964
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reward modeling has emerged as a promising approach for the scalable alignment of language models. However, contemporary reward models (RMs) often lack robustness, awarding high rewards to low-quality, out-of-distribution (OOD) samples. This can lead to reward hacking, where policies exploit unintended shortcuts to maximize rewards, undermining alignment. To address this challenge, we introduce Adv-RM, a novel adversarial training framework that automatically identifies adversarial examples -- responses that receive high rewards from the target RM but are OOD and of low quality. By leveraging reinforcement learning, Adv-RM trains a policy to generate adversarial examples that reliably expose vulnerabilities in large state-of-the-art reward models such as Nemotron 340B RM. Incorporating these adversarial examples into the reward training process improves the robustness of RMs, mitigating reward hacking and enhancing downstream performance in RLHF. We demonstrate that Adv-RM significantly outperforms conventional RM training, increasing stability and enabling more effective RLHF training in both synthetic and real-data settings.

Related papers

• Energy-Based Reward Models for Robust Language Model Alignment [9.843359827321194]
  We introduce Energy-Based Reward Model (EBRM), a lightweight post-hoc refinement framework for Reward Models (RMs) EBRM models the reward distribution explicitly, capturing uncertainty in human preferences and mitigating the impact of noisy or misaligned annotations. Empirical evaluations demonstrate significant improvements in robustness and generalization, achieving up to a 5.97% improvement in safety-critical alignment tasks.
  arXiv  Detail & Related papers  (2025-04-17T17:47:15Z)
• Probabilistic Uncertain Reward Model: A Natural Generalization of Bradley-Terry Reward Model [27.40414952747553]
  We propose Probabilistic Uncertain Reward Model (PURM) to address reward hacking.<n>Experiments demonstrate PURM significantly delays the onset of reward hacking while improving final reward performance.
  arXiv  Detail & Related papers  (2025-03-28T14:39:52Z)
• Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems [54.4392552373835]
  Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs)<n>We propose agentic reward modeling, a reward system that combines reward models with verifiable correctness signals to provide reliable rewards.<n>We conduct comprehensive experiments on existing reward model benchmarks and inference time best-of-n searches on real-world downstream tasks.
  arXiv  Detail & Related papers  (2025-02-26T17:19:12Z)
• Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs [58.18140409409302]
  Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL)<n>Applying RL in broader domains like chatbots and content generation presents unique challenges.<n>We show a case study of reproducing existing reward model ensemble research using embedding-based reward models.
  arXiv  Detail & Related papers  (2025-02-04T19:37:35Z)
• Reward-Robust RLHF in LLMs [25.31456438114974]
  Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence. The reliance on reward-model-based (RM-based) alignment methods introduces significant challenges. We introduce a reward-robust RLHF framework aimed at addressing these fundamental challenges.
  arXiv  Detail & Related papers  (2024-09-18T02:35:41Z)
• Semi-Supervised Reward Modeling via Iterative Self-Training [52.48668920483908]
  We propose Semi-Supervised Reward Modeling (SSRM), an approach that enhances RM training using unlabeled data. We demonstrate that SSRM significantly improves reward models without incurring additional labeling costs. Overall, SSRM substantially reduces the dependency on large volumes of human-annotated data, thereby decreasing the overall cost and time involved in training effective reward models.
  arXiv  Detail & Related papers  (2024-09-10T22:57:58Z)
• WARM: On the Benefits of Weight Averaged Reward Models [63.08179139233774]
  We propose Weight Averaged Reward Models (WARM) to mitigate reward hacking. Experiments on summarization tasks, using best-of-N and RL methods, shows that WARM improves the overall quality and alignment of LLM predictions.
  arXiv  Detail & Related papers  (2024-01-22T18:27:08Z)
• The Trickle-down Impact of Reward (In-)consistency on RLHF [71.37987812944971]
  We show that reward inconsistency exhibits a trickle-down effect on the downstream Reinforcement Learning from Human Feedback process. We propose Contrast Instructions -- a benchmarking strategy for the consistency of RM. We show that RLHF models trained with a more consistent RM yield more useful responses.
  arXiv  Detail & Related papers  (2023-09-28T04:05:13Z)
• Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning [19.788336796981685]
  We propose a novel Distributional Reward Estimation framework for effective Multi-Agent Reinforcement Learning (DRE-MARL) Our main idea is to design the multi-action-branch reward estimation and policy-weighted reward aggregation for stabilized training. The superiority of the DRE-MARL is demonstrated using benchmark multi-agent scenarios, compared with the SOTA baselines in terms of both effectiveness and robustness.
  arXiv  Detail & Related papers  (2022-10-14T08:31:45Z)
• Transferring Adversarial Robustness Through Robust Representation Matching [3.5934248574481717]
  Adrial training is one of the few known defenses able to reliably withstand such attacks against neural networks. We propose Robust Representation Matching (RRM), a low-cost method to transfer the robustness of an adversarially trained model to a new model. RRM is superior with respect to both model performance and adversarial training time.
  arXiv  Detail & Related papers  (2022-02-21T05:15:40Z)

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.