Stable Preference Optimization for LLMs: A Bilevel Approach Beyond Direct Preference Optimization

• URL: http://arxiv.org/abs/2507.07723v1
• Date: Thu, 10 Jul 2025 12:57:39 GMT
• Title: Stable Preference Optimization for LLMs: A Bilevel Approach Beyond Direct Preference Optimization
• Authors: Chengtao Jian, Kai Yang, Ye Ouyang, Xiaozhou Ye,
• Abstract summary: We present a comprehensive analysis of DPO's dynamics from a probability evolution perspective.<n>We propose a theoretically grounded bilevel optimization framework that tightly integrate supervised fine-tuning with an enhanced DPO objective a.k.a. stable preference optimization.
• Score: 2.384797824772941
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Direct Preference Optimization (DPO) has emerged as a popular and efficient alternative to reward modeling and reinforcement learning for aligning language models with human preferences. Despite its empirical success, the theoretical properties and intrinsic limitations of DPO remain underexplored. In this work, we first present a comprehensive analysis of DPO's dynamics from a probability evolution perspective. Our analysis reveals that DPO is highly sensitive to initialization. It also tends to misallocate probability mass, which can inadvertently shift probability toward irrelevant or undesired responses. This misallocation may unintentionally reinforce model bias, thereby compromising both the stability of model alignment and the consistency with intended preferences. Motivated by these theoretical findings, we propose a theoretically grounded bilevel optimization framework that tightly integrate supervised fine-tuning with an enhanced DPO objective a.k.a. stable preference optimization. Our approach introduces a principled regularization scheme to explicitly encourage absolute probability improvement for preferred outputs, while maintaining stable optimization dynamics. Experiments on challenging reasoning and summarization benchmarks elucidate that our method consistently improves reasoning accuracy and better aligns output distributions with intended preferences, outperforming standard DPO. Stable preference optimization provides new insights into the design of preference-based alignment objectives and opens up new avenues towards more reliable and interpretable language model alignment.

Related papers

• Divergence Minimization Preference Optimization for Diffusion Model Alignment [58.651951388346525]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>Our results show that diffusion models fine-tuned with DMPO can consistently outperform or match existing techniques.<n>DMPO unlocks a robust and elegant pathway for preference alignment, bridging principled theory with practical performance in diffusion models.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning [14.034412856423529]
  Direct Preference Optimization (DPO) has gained attention for its simplicity and computational efficiency in aligning large language models (LLMs)<n>Recent advancements have extended DPO to multimodal scenarios, achieving strong performance.<n>Traditional DPO relies on binary preference optimization, rewarding or penalizing entire responses without considering fine-grained segment correctness.<n>We propose Adaptive Sentence-level Preference Optimization (ASPO), which evaluates individual sentences for more precise preference optimization.
  arXiv  Detail & Related papers  (2025-05-25T11:33:08Z)
• SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment [46.55132297735257]
  We propose a novel Self-Guided Direct Preference Optimization algorithm, i.e., SGDPO, which incorporates a pilot term to steer the gradient flow during the optimization process.<n>We provide a detailed theoretical analysis of our proposed method and elucidate its operational mechanism.
  arXiv  Detail & Related papers  (2025-05-18T14:19:23Z)
• Preference-Guided Diffusion for Multi-Objective Offline Optimization [64.08326521234228]
  We propose a preference-guided diffusion model for offline multi-objective optimization.<n>Our guidance is a preference model trained to predict the probability that one design dominates another.<n>Our results highlight the effectiveness of classifier-guided diffusion models in generating diverse and high-quality solutions.
  arXiv  Detail & Related papers  (2025-03-21T16:49:38Z)
• A Survey of Direct Preference Optimization [103.59317151002693]
  Large Language Models (LLMs) have demonstrated unprecedented generative capabilities.<n>Their alignment with human values remains critical for ensuring helpful and harmless deployments.<n>Direct Preference Optimization (DPO) has recently gained prominence as a streamlined alternative.
  arXiv  Detail & Related papers  (2025-03-12T08:45:15Z)
• Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models [54.381650481255235]
  We introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (O) Our approach leverages a search-based optimization framework that allows LLMs to iteratively self-improve and craft the optimal alignment instructions. Empirical evaluations on eight recent LLMs, both open and closed-sourced, demonstrate that DRPO significantly enhances alignment performance.
  arXiv  Detail & Related papers  (2024-11-13T16:15:38Z)
• Understanding Likelihood Over-optimisation in Direct Alignment Algorithms [20.043560907227018]
  Direct Alignment Algorithms (DAAs) have emerged as alternatives to online Reinforcement Learning from Human Feedback. These algorithms aim to increase the likelihood of generating better (preferred) completions while discouraging worse (non-preferred) ones. This work explores the relationship between completion likelihood and model performance in state-of-the-art DAAs.
  arXiv  Detail & Related papers  (2024-10-15T15:14:22Z)
• $α$-DPO: Adaptive Reward Margin is What Direct Preference Optimization Needs [45.46582930202524]
  $alpha$-DPO is an adaptive preference optimization algorithm for large language models. It balances the policy model and the reference model to achieve personalized reward margins. It consistently outperforms DPO and SimPO across various model settings.
  arXiv  Detail & Related papers  (2024-10-14T04:29:57Z)
• Accelerated Preference Optimization for Large Language Model Alignment [60.22606527763201]
  Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO) formulates RLHF as a policy optimization problem without explicitly estimating the reward function. We propose a general Accelerated Preference Optimization (APO) framework, which unifies many existing preference optimization algorithms.
  arXiv  Detail & Related papers  (2024-10-08T18:51:01Z)
• 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)
• Statistical Rejection Sampling Improves Preference Optimization [42.57245965632205]
  We introduce a novel approach to source preference data from the target optimal policy using rejection sampling. We also propose a unified framework that enhances the loss functions used in both Sequence Likelihood (SLiC) and Direct Preference Optimization (DPO) from a preference modeling standpoint.
  arXiv  Detail & Related papers  (2023-09-13T01:07:25Z)

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.