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

arXiv:2604.24952 · cs.CV, cs.AI · Submitted 2026-04-27 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-04-27

Updated: 2026-09-30

Comments: 21 pages. Published as a conference paper at ICLR 2026

Code: https://github.com/L-CodingSpace/semi-dpo

Project page: https://liming-ai.github.io/SemiDPO

License: http://creativecommons.org/licenses/by-nc-sa/4.0/

The gist: Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment.

Terminology

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

Sources

Related papers