Risk-aware Direct Preference Optimization under Nested Risk Measure

• URL: http://arxiv.org/abs/2505.20359v2
• Date: Thu, 29 May 2025 13:19:08 GMT
• Title: Risk-aware Direct Preference Optimization under Nested Risk Measure
• Authors: Lijun Zhang, Lin Li, Yajie Qi, Huizhong Song, Yaodong Yang, Jun Wang, Wei Wei,
• Abstract summary: Risk-aware Direct Preference Optimization (Ra-DPO) is a novel approach that incorporates risk-awareness by employing a class of nested risk measures.<n> Experimental results across three open-source datasets demonstrate the proposed method's superior performance in balancing alignment performance and model drift.
• Score: 23.336246526648374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When fine-tuning pre-trained Large Language Models (LLMs) to align with human values and intentions, maximizing the estimated reward can lead to superior performance, but it also introduces potential risks due to deviations from the reference model's intended behavior. Most existing methods typically introduce KL divergence to constrain deviations between the trained model and the reference model; however, this may not be sufficient in certain applications that require tight risk control. In this paper, we introduce Risk-aware Direct Preference Optimization (Ra-DPO), a novel approach that incorporates risk-awareness by employing a class of nested risk measures. This approach formulates a constrained risk-aware advantage function maximization problem and then converts the Bradley-Terry model into a token-level representation. The objective function maximizes the likelihood of the policy while suppressing the deviation between a trained model and the reference model using a sequential risk ratio, thereby enhancing the model's risk-awareness. Experimental results across three open-source datasets: IMDb Dataset, Anthropic HH Dataset, and AlpacaEval, demonstrate the proposed method's superior performance in balancing alignment performance and model drift. Our code is opensourced at https://github.com/zlj123-max/Ra-DPO.

Related papers

• Towards Reliable, Uncertainty-Aware Alignment [12.63619480522393]
  We study the variability of reward model training on open-source benchmarks.<n>We propose a variance-aware policy optimization framework for preference-based alignment.
  arXiv  Detail & Related papers  (2025-07-21T12:51:29Z)
• Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling [84.00480999255628]
  Reinforcement Learning algorithms for safety alignment of Large Language Models (LLMs) encounter the challenge of distribution shift.<n>Current approaches typically address this issue through online sampling from the target policy.<n>We propose a new framework that leverages the model's intrinsic safety judgment capability to extract reward signals.
  arXiv  Detail & Related papers  (2025-03-13T06:40:34Z)
• Mitigating optimistic bias in entropic risk estimation and optimization with an application to insurance [5.407319151576265]
  The entropic risk measure is widely used to account for tail risks associated with an uncertain loss.<n>To mitigate the bias in the empirical entropic risk estimator, we propose a strongly consistent bootstrapping procedure.<n>We show that our methods suggest a higher (and more accurate) premium to homeowners.
  arXiv  Detail & Related papers  (2024-09-30T04:02:52Z)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization [63.93275508300137]
  We introduce a novel risk-aware Counterfactual Learning To Rank method with theoretical guarantees for safe deployment. Our experimental results demonstrate the efficacy of our proposed method, which is effective at avoiding initial periods of bad performance when little data is available.
  arXiv  Detail & Related papers  (2023-04-26T15:54:23Z)
• Optimizing the Performative Risk under Weak Convexity Assumptions [0.0]
  In performative prediction, a predictive model impacts the distribution that generates future data. Prior work has identified a pair of general conditions on the loss and the mapping from model parameters to distributions that implies convexity the performative risk. In this paper, we relax these assumptions, without sacrificing the amenability of the performative minimization risk problem for iterative optimization methods.
  arXiv  Detail & Related papers  (2022-09-02T01:07:09Z)
• Efficient Risk-Averse Reinforcement Learning [79.61412643761034]
  In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns. We prove that under certain conditions this inevitably leads to a local-optimum barrier, and propose a soft risk mechanism to bypass it. We demonstrate improved risk aversion in maze navigation, autonomous driving, and resource allocation benchmarks.
  arXiv  Detail & Related papers  (2022-05-10T19:40:52Z)
• Modeling the Second Player in Distributionally Robust Optimization [90.25995710696425]
  We argue for the use of neural generative models to characterize the worst-case distribution. This approach poses a number of implementation and optimization challenges. We find that the proposed approach yields models that are more robust than comparable baselines.
  arXiv  Detail & Related papers  (2021-03-18T14:26:26Z)
• Risk-Averse Offline Reinforcement Learning [46.383648750385575]
  Training Reinforcement Learning (RL) agents in high-stakes applications might be too prohibitive due to the risk associated to exploration. We present the Offline Risk-Averse Actor-Critic (O-RAAC), a model-free RL algorithm that is able to learn risk-averse policies in a fully offline setting.
  arXiv  Detail & Related papers  (2021-02-10T10:27:49Z)
• How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches? [33.65954640678556]
  Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source domain and unlabeled samples from the target domain. E-MixNet employs enhanced mixup, a generic vicinal distribution, on the labeled source samples and pseudo-labeled target samples to calculate a proxy of the combined risk.
  arXiv  Detail & Related papers  (2020-12-30T00:46:57Z)
• Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning [75.17074235764757]
  We present a framework for risk-averse control in a discounted infinite horizon MDP. MVPI enjoys great flexibility in that any policy evaluation method and risk-neutral control method can be dropped in for risk-averse control off the shelf. This flexibility reduces the gap between risk-neutral control and risk-averse control and is achieved by working on a novel augmented MDP.
  arXiv  Detail & Related papers  (2020-04-22T22:23:44Z)

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.