Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation

• URL: http://arxiv.org/abs/2609.06893v1
• Date: Mon, 07 Sep 2026 00:33:50 GMT
• Title: Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation
• Abstract summary: Direct preference optimization (DPO) is a promising offline approach for aligning large language models (LLMs)<n>In this paper, we propose Distilled Preference Probability Policy Optimization (DP3O) as an effective and efficient offline alignment algorithm.<n>We show that DP3O achieves performance comparable to iterative DPO and reduces training time by about $42%$.
• Score: 15.685915630621139
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Direct preference optimization DPO is a promising offline approach for aligning large language models (LLMs) due to its simplicity, computational efficiency, and implicit modeling of human preferences. Interestingly, iterative extensions of DPO have achieved stronger performance on academic benchmarks, raising two key questions: (i) Why do iterative methods generally outperform offline ones? (ii) Can their advantages be incorporated into offline alignment? To answer the first question, our controlled experiments reveal that the explicit preference model, additionally introduced in the iterative procedure, is a key factor behind its superiority over offline methods. This insight leads us to answer the second question affirmatively and propose Distilled Preference Probability Policy Optimization (DP3O), an effective and efficient offline alignment algorithm. DP3O first learns an explicit preference model using a helper class of LLMs and then distills its knowledge into policy optimization. Theoretically, we show that explicit preference modeling admits better estimation error control than implicit formulations, and that DP3O achieves a tighter generalization bound than hard-label DPO through variance reduction. Empirically, we evaluate DP3O on a wide range of chat-based and downstream tasks and show that it outperforms state-of-the-art offline methods, achieves performance comparable to iterative DPO, and reduces training time by about $42\%$, demonstrating both its effectiveness and efficiency.

Related papers

• dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models [71.26391195427878]
  Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation.<n>In this work, we aim to improve the policy optimization for dLLMs by reducing the cost of the trajectory probability calculation.<n>We evaluate dTRPO on 7B dLLMs across instruction-following and reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-19T11:55:52Z)
• Adaptive Preference Optimization with Uncertainty-aware Utility Anchor [33.74005997646761]
  offline preference optimization methods are efficient for large language models (LLMs) alignment.<n>We propose a general framework for offline preference optimization methods, which introduces an anchoring function to estimate the uncertainties brought from preference data annotation.<n>Our method enables training even in scenarios where the data is unpaired, significantly enhancing data utilization efficiency.
  arXiv  Detail & Related papers  (2025-09-03T10:20:08Z)
• Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization [13.97375970293678]
  DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability.<n>We propose Linear Preference Optimization (LPO), a novel alignment framework featuring three key innovations.<n>First, we introduce gradient decoupling by replacing the log-sigmoid function with an absolute difference loss, thereby isolating the optimization dynamics.<n>Second, we improve stability through an offset constraint combined with a positive regularization term to preserve the chosen response quality.<n>Third, we implement controllable rejection suppression using gradient separation with straightforward estimation and a tunable coefficient that linearly regulates the descent of the rejection probability.
  arXiv  Detail & Related papers  (2025-08-20T10:17:29Z)
• ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood [14.512464277772194]
  Aligned Supervised Fine-Tuning (ASFT) is an effective approach that better aligns Large Language Models with pair-wise datasets. ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data. Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
  arXiv  Detail & Related papers  (2024-09-14T11:39:13Z)
• 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)
• Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization [78.82586283794886]
  $chi2$-Preference Optimization ($chi$PO) is an efficient offline alignment algorithm provably robust to overoptimization.<n>$chi$PO implements the principle of pessimism in the face of uncertainty via regularization.<n>$chi$PO's simplicity and strong guarantees make it the first practical and general-purpose offline alignment algorithm provably robust to overoptimization.
  arXiv  Detail & Related papers  (2024-07-18T11:08:40Z)
• SAIL: Self-Improving Efficient Online Alignment of Large Language Models [56.59644677997827]
  Reinforcement Learning from Human Feedback is a key method for aligning large language models with human preferences. Recent literature has focused on designing online RLHF methods but still lacks a unified conceptual formulation. Our approach significantly improves alignment performance on open-sourced datasets with minimal computational overhead.
  arXiv  Detail & Related papers  (2024-06-21T18:05:35Z)
• The Importance of Online Data: Understanding Preference Fine-tuning via Coverage [25.782644676250115]
  We study the similarities and differences between online and offline techniques for preference fine-tuning. We prove that a global coverage condition is both necessary and sufficient for offline contrastive methods to converge to the optimal policy. We derive a hybrid preference optimization algorithm that uses offline data for contrastive-based preference optimization and online data for KL regularization.
  arXiv  Detail & Related papers  (2024-06-03T15:51:04Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
  Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice. We propose efficient exact optimization (EXO) of the alignment objective.
  arXiv  Detail & Related papers  (2024-02-01T18:51:54Z)

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.