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

• URL: http://arxiv.org/abs/2604.24952v1
• Date: Mon, 27 Apr 2026 19:49:04 GMT
• Title: Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
• Abstract summary: We show that compressing multi-dimensional preferences into binary labels generates conflicting gradient signals.<n>We propose Semi-DPO, a semi-supervised approach that treats consistent pairs as clean labeled data and conflicting ones as noisy unlabeled data.
• Score: 22.08509360975174
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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

Related papers

• Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation [6.262888209373497]
  We investigate how language models encode preference information in their intermediate representations.<n>We find that activations from chosen and rejected responses form distinct clusters across layers, even in pretrained models.<n>Exploiting this structure, we propose training a lightweight linear probe on a few labelled preference pairs and using it to annotate large unlabelled datasets.
  arXiv  Detail & Related papers  (2026-08-31T14:52:19Z)
• FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients [36.01783797965344]
  Federated learning (FL) suffers from performance degradation due to the presence of noisy annotations in distributed scenarios.<n>We propose method(textbfFederated under textbfRepresentation textbfGemometry) to recognize noisy labels.
  arXiv  Detail & Related papers  (2026-03-20T08:01:04Z)
• Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision [14.612317970237436]
  Diffusion models have achieved impressive results in generative tasks such as text-to-image synthesis.<n>They often struggle to fully align outputs with nuanced user intent and maintain consistent aesthetic quality.<n>Existing preference-based training methods help address these issues but rely on costly and potentially noisy human datasets.
  arXiv  Detail & Related papers  (2025-12-29T12:46:07Z)
• Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation [51.67328507400985]
  In noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators.<n>This paper focuses on learning from partial labels annotated by pre-trained vision-language models.<n>It proposes an innovative collaborative consistency regularization (Co-Reg) method.
  arXiv  Detail & Related papers  (2025-06-03T12:48:54Z)
• Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences [13.588231827053923]
  Direct Preference Optimization (DPO) aligns text-to-image (T2I) generation models with human preferences using pairwise preference data.<n>We propose SmPO-Diffusion, a novel method for modeling preference distributions to improve the DPO objective.<n>Our approach effectively mitigates issues of excessive optimization and objective misalignment present in existing methods.
  arXiv  Detail & Related papers  (2025-06-03T09:47:22Z)
• Geometric-Averaged Preference Optimization for Soft Preference Labels [78.2746007085333]
  Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic.<n>In this work, we introduce the distributional soft preference labels and improve Direct Preference Optimization (DPO) with a weighted geometric average of the LLM output likelihood in the loss function.
  arXiv  Detail & Related papers  (2024-09-10T17:54:28Z)
• Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models with human preferences.<n>Our key idea is leveraging the human prior knowledge within the small (seed) data.<n>We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• Manifold DivideMix: A Semi-Supervised Contrastive Learning Framework for Severe Label Noise [4.90148689564172]
  Real-world datasets contain noisy label samples that have no semantic relevance to any class in the dataset. Most state-of-the-art methods leverage ID labeled noisy samples as unlabeled data for semi-supervised learning. We propose incorporating the information from all the training data by leveraging the benefits of self-supervised training.
  arXiv  Detail & Related papers  (2023-08-13T23:33:33Z)
• Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels [61.97359362447732]
  Learning from noisy labels is an important and long-standing problem in machine learning for real applications. In this paper, we reformulate the label-noise problem from a generative-model perspective. Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets.
  arXiv  Detail & Related papers  (2023-05-31T03:01:36Z)
• Neighborhood Collective Estimation for Noisy Label Identification and Correction [92.20697827784426]
  Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. Recent advances employ the predicted label distributions of individual samples to perform noise verification and noisy label correction, easily giving rise to confirmation bias. We propose Neighborhood Collective Estimation, in which the predictive reliability of a candidate sample is re-estimated by contrasting it against its feature-space nearest neighbors.
  arXiv  Detail & Related papers  (2022-08-05T14:47:22Z)

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.