Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization

• URL: http://arxiv.org/abs/2503.18130v1
• Date: Sun, 23 Mar 2025 16:20:59 GMT
• Title: Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
• Authors: Juntao Dai, Taiye Chen, Yaodong Yang, Qian Zheng, Gang Pan,
• Abstract summary: We propose the Behavior-Supported Policy Optimization (BSPO) method to mitigate the reward over-optimization issue.<n>BSPO reduces the generation of OOD responses during the reinforcement learning process.<n> Empirical results show that BSPO outperforms baselines in preventing reward over-optimization.
• Score: 23.817251267022847
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an open challenge leading to discrepancies between the performance of LLMs under the reward model and the true human objectives. A primary contributor to reward over-optimization is the extrapolation error that arises when the reward model evaluates out-of-distribution (OOD) responses. However, current methods still fail to prevent the increasing frequency of OOD response generation during the reinforcement learning (RL) process and are not effective at handling extrapolation errors from OOD responses. In this work, we propose the Behavior-Supported Policy Optimization (BSPO) method to mitigate the reward over-optimization issue. Specifically, we define behavior policy as the next token distribution of the reward training dataset to model the in-distribution (ID) region of the reward model. Building on this, we introduce the behavior-supported Bellman operator to regularize the value function, penalizing all OOD values without impacting the ID ones. Consequently, BSPO reduces the generation of OOD responses during the RL process, thereby avoiding overestimation caused by the reward model's extrapolation errors. Theoretically, we prove that BSPO guarantees a monotonic improvement of the supported policy until convergence to the optimal behavior-supported policy. Empirical results from extensive experiments show that BSPO outperforms baselines in preventing reward over-optimization due to OOD evaluation and finding the optimal ID policy.

Related papers

• Entropy-Regularized Process Reward Model [30.279394036823092]
  Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning.<n>We propose an entropy-regularized process reward model (ER-PRM) that integrates KL-regularized Markov Decision Processes (MDP)<n>Our empirical experiments on the MATH and GSM8K benchmarks demonstrate that ER-PRM consistently outperforms existing process reward models.
  arXiv  Detail & Related papers  (2024-12-15T01:09:23Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
  We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset. We show that our approach consistently boosts DPO by a considerable margin. Our method not only maximizes the utility of preference data but also mitigates the issue of unlearning, demonstrating its broad effectiveness beyond mere data expansion.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs [25.011675414622392]
  This study introduces a novel approach to enhance the reward model's generalization ability against distribution shifts. We retain the base model's language model head and incorporate a suite of text-generation losses to preserve the hidden states' text-generation capabilities. Our experimental results demonstrate that the introduced regularization technique markedly improves the accuracy of learned reward models.
  arXiv  Detail & Related papers  (2024-06-14T17:49:59Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards [26.40009657912622]
  Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable and sensitive to noise from various sources. In this work, we improve the effectiveness of the reward model by introducing a penalty term on the reward, named as textitcontrastive rewards
  arXiv  Detail & Related papers  (2024-03-12T14:51:57Z)
• Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation [46.61909578101735]
  Adversarial Policy Optimization (AdvPO) is a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback. In this paper, we introduce a lightweight way to quantify uncertainties in rewards, relying solely on the last layer embeddings of the reward model.
  arXiv  Detail & Related papers  (2024-03-08T09:20:12Z)
• Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble [67.4269821365504]
  Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data. We contribute a reward ensemble method that allows the reward model to make more accurate predictions.
  arXiv  Detail & Related papers  (2024-01-30T00:17:37Z)
• Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles [26.955375398765085]
  Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs) In this paper, we observe the weakness of KL regularization which is commonly employed in existing RLHF methods to address overoptimization. We propose uncertainty-penalized RLHF (UP-RLHF), which incorporates uncertainty regularization during RL-finetuning.
  arXiv  Detail & Related papers  (2023-12-30T14:14:14Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• Policy Gradient Bayesian Robust Optimization for Imitation Learning [49.881386773269746]
  We derive a novel policy gradient-style robust optimization approach, PG-BROIL, to balance expected performance and risk. Results suggest PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse.
  arXiv  Detail & Related papers  (2021-06-11T16:49:15Z)

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.