English

Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization

Computer Vision and Pattern Recognition 2026-04-29 v1 Artificial Intelligence

Abstract

Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resulting in severe label noise: images that excel in some dimensions but are deficient in others are simply marked as winner or loser. We theoretically demonstrate that compressing multi-dimensional preferences into binary labels generates conflicting gradient signals that misguide Diffusion Direct Preference Optimization (DPO). To address this, we propose Semi-DPO, a semi-supervised approach that treats consistent pairs as clean labeled data and conflicting ones as noisy unlabeled data. Our method starts by training on a consensus-filtered clean subset, then uses this model as an implicit classifier to generate pseudo-labels for the noisy set for iterative refinement. Experimental results demonstrate that Semi-DPO achieves state-of-the-art performance and significantly improves alignment with complex human preferences, without requiring additional human annotation or explicit reward models during training. We will release our code and models at: https://github.com/L-CodingSpace/semi-dpo

Keywords

Cite

@article{arxiv.2604.24952,
  title  = {Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization},
  author = {Xinxin Liu and Ming Li and Zonglin Lyu and Yuzhang Shang and Chen Chen},
  journal= {arXiv preprint arXiv:2604.24952},
  year   = {2026}
}
R2 v1 2026-07-01T12:38:04.102Z