ADPO: Anchored Direct Preference Optimization
We present Anchored Direct Preference Optimization (ADPO), a policy alignment method derived from first principles of KL-regularized reinforcement learning. Unlike standard approaches that treat the reference policy merely as a regularizer, we show that the optimal policy in reinforcement learning from human feedback inherently operates in a differential coordinate system, optimizing relative advantage in the form of log ratios rather than absolute probabilities. ADPO explicitly parameterizes this optimal structure through anchored logits, effectively decoupling response quality from prior popularity and creating an implicit trust region through curvature scaling. We show that this formulation unifies supervised fine-tuning, reinforcement learning, and ranking-based objectives under a single geometric perspective. Theoretically, ADPO resolves the probability smearing problem of supervised fine-tuning while avoiding the mode-seeking instability characteristic of reverse-KL methods. Empirically, the listwise ranking variant of ADPO achieves state-of-the-art performance on reasoning tasks, outperforming GRPO by 30.9 percent on Qwen3-1.7B and demonstrating superior robustness under distribution shift.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
Large Video Models (LVMs) built upon Large Language Models (LLMs) have shown promise in video understanding but often suffer from misalignment with human intuition and video hallucination issues. To address these challen…
HallucinationVideo UnderstandingAPO: Alpha-Divergence Preference Optimization
Two divergence regimes dominate modern alignment practice. Supervised fine-tuning and many distillation-style objectives implicitly minimize the forward KL divergence KL(q || pi_theta), yielding stable mode-covering upda…
Reinforcement LearningMargin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization
Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models. However, its reliance on a fixed temperature parameter leads to suboptimal training on diverse prefere…
AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates
DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loop. Recent theoretical analysis uncovers an asymmetric gradient behav…
Autoregressive Direct Preference Optimization
Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However, the widespread reliance on the response-level Bradley-Terry (BT) model m…