Understanding the Impact of Sampling Quality in Direct Preference Optimization

• URL: http://arxiv.org/abs/2506.04272v2
• Date: Sat, 11 Oct 2025 01:06:10 GMT
• Title: Understanding the Impact of Sampling Quality in Direct Preference Optimization
• Authors: Kyung Rok Kim, Yumo Bai, Chonghuan Wang, Guanting Chen,
• Abstract summary: We study how data of higher quality can be leveraged to improve performance in Direct Preference Optimization (DPO)<n>Our analyses show that both the solution space and the convergence behavior of DPO depend on the support and quality of the data-generating distribution.
• Score: 4.122673728216191
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study how data of higher quality can be leveraged to improve performance in Direct Preference Optimization (DPO), aiming to understand its impact on DPO training dynamics. Our analyses show that both the solution space and the convergence behavior of DPO depend on the support and quality of the data-generating distribution. We first analyze how data and reference policy influence policy updates during gradient descent, and how a practical phenomenon known as likelihood displacement can interfere with the desired dynamics. We then design a simplified yet well-structured alignment model as a proxy that preserves most of the beneficial properties of RLHF while avoiding likelihood displacement. Based on this model, we develop quantitative results showing how more frequent high-quality responses amplify the gradient signal and improve the optimization landscape, leading to more effective policy learning. Our theoretical findings are supported by empirical experiments and provide a principled justification for the online DPO framework in practice.

Related papers

• How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics [65.67654005892469]
  We show that proper instance-dependent sampling can yield stronger ranking guarantees, while skewed on-policy sampling can induce excessive concentration under structured preferences.<n>We then analyze iterative alignment dynamics in which the learned policy feeds back into future sampling and reference policies.<n>Our theoretical insights extend to Direct Preference Optimization, indicating the phenomena we captured are common to a broader class of preference-alignment methods.
  arXiv  Detail & Related papers  (2026-02-12T17:11:08Z)
• AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models [54.56296715999545]
  Reinforcement learning from human feedback shows promise for aligning diffusion and flow models.<n>Policy optimization methods such as GRPO suffer from inefficient and static sampling strategies.<n>We propose Adaptive Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy.
  arXiv  Detail & Related papers  (2026-02-06T16:09:50Z)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping [69.74252624161652]
  We propose BAlanced Policy Optimization with Adaptive Clipping (BAPO)<n>BAPO dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization.<n>On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B.
  arXiv  Detail & Related papers  (2025-10-21T12:55:04Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• What Matters in Data for DPO? [6.208229499655634]
  Direct Preference Optimization (DPO) has emerged as a simple and effective approach for aligning large language models with human preferences.<n>We provide a systematic study of how preference data distribution influences DPO, from both theoretical and empirical perspectives.<n>We show that the quality of chosen responses plays a dominant role in optimizing the DPO objective, while the quality of rejected responses may have relatively limited impact.
  arXiv  Detail & Related papers  (2025-08-23T16:00:30Z)
• Improving DAPO from a Mixed-Policy Perspective [0.0]
  This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm.<n>We first propose a method that incorporates a pre-trained, stable guiding policy to provide off-policy experience.<n>We then extend this idea to re-utilize zero-reward samples, which are often discarded by dynamic sampling strategies.
  arXiv  Detail & Related papers  (2025-07-17T09:12:09Z)
• Stable Preference Optimization for LLMs: A Bilevel Approach Beyond Direct Preference Optimization [2.384797824772941]
  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.
  arXiv  Detail & Related papers  (2025-07-10T12:57:39Z)
• Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization [35.335072390336855]
  We study the goal of preference optimization as learning the differential information required to update a reference policy into a target policy.<n>First, we find that DPO's log-ratio reward is uniquely justified when preferences encode the Differential Information needed to update a reference policy into the target policy.<n>Second, we discuss how commonly observed training dynamics in DPO, including changes in log-likelihood and policy exploration, stem from a power-law DID relationship.
  arXiv  Detail & Related papers  (2025-05-29T17:59:50Z)
• Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO [51.22869332661607]
  We decompose the performance gap between reinforcement learning from human feedback and direct preference optimization under a representation gap.<n>We show that RLHF, DPO, or online DPO can outperform one another depending on the type of model mis-specifications.
  arXiv  Detail & Related papers  (2025-05-26T09:54:02Z)
• 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)
• 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)
• Gradient Imbalance in Direct Preference Optimization [26.964127989679596]
  We propose Balanced-DPO, a simple yet effective modification to the DPO objective that introduces a computationally efficient gradient reweighting mechanism.<n>Our experiments demonstrate the effectiveness of Balanced-DPO, validating the theoretical findings and confirming that addressing gradient imbalance is key to improving DPO's performance.
  arXiv  Detail & Related papers  (2025-02-28T08:47:03Z)
• Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking [50.325021634589596]
  We propose a Tailored Optimization Preference (TailorPO) framework for aligning diffusion models with human preference.<n>Our approach directly ranks intermediate noisy samples based on their step-wise reward, and effectively resolves the gradient direction issues.<n> Experimental results demonstrate that our method significantly improves the model's ability to generate aesthetically pleasing and human-preferred images.
  arXiv  Detail & Related papers  (2025-02-01T16:08:43Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• 3D-Properties: Identifying Challenges in DPO and Charting a Path Forward [17.27880657597116]
  We revisit DPO, analyzing its theoretical foundations and empirical performance.<n>We identify three key properties, termed 3D properties, that emerge from DPO's learning process.<n>We propose simple regularization techniques that improve training stability and performance.
  arXiv  Detail & Related papers  (2024-06-11T14:59:24Z)
• Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization [55.97310586039358]
  Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality.<n>We propose a novel model-free diffusion-based online RL algorithm, Q-weighted Variational Policy Optimization (QVPO)<n>Specifically, we introduce the Q-weighted variational loss, which can be proved to be a tight lower bound of the policy objective in online RL under certain conditions.<n>We also develop an efficient behavior policy to enhance sample efficiency by reducing the variance of the diffusion policy during online interactions.
  arXiv  Detail & Related papers  (2024-05-25T10:45:46Z)
• 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)

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.