提出无需训练的闭式解法，同时消除视觉与文本偏见且保证性能损失有限。
A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasks
- 在跨模态空间中求得闭式解，直接优化公平性与性能平衡
- 在零样本图像分类等任务上实现更优的群体与交叉公平性表现
- 无需标注数据和训练，适合快速部署到各类视觉语言任务
尽管视觉语言模型在多种下游任务中表现优异，但其可能继承训练数据中的社会偏见，并在实际应用中进一步传播。现有去偏方法大多仅关注公平性，缺乏对模型性能保留的理论保障。本文提出一种训练无关的去偏方法，在跨模态空间中获得闭式解，实现帕累托最优公平性并保证有界性能损失。该方法无需标注数据，可联合去除非特定模态的偏见，适用于多种下游任务。大量实验表明，该方法在零样本图像分类、文本到图像检索与生成等任务中，优于现有方法，在群体及交叉公平性指标上均有提升，同时保持任务性能稳定。
原文摘要 · Abstract (English)
While Vision-Language Models (VLMs) have achieved remarkable performance across diverse downstream tasks, recent studies have shown that they can inherit social biases from the training data and further propagate them into downstream applications. To address this issue, various debiasing approaches have been proposed, yet most of them aim to improve fairness without having a theoretical guarantee that the utility of the model is preserved. In this paper, we introduce a debiasing method that yields a \textbf{closed-form} solution in the cross-modal space, achieving Pareto-optimal fairness with \textbf{bounded utility losses}. Our method is \textbf{training-free}, requires \textbf{no annotated data}, and can jointly debias both visual and textual modalities across downstream tasks. Extensive experiments show that our method outperforms existing methods in debiasing VLMs across diverse fairness metrics and datasets for both group and \textbf{intersectional} fairness in downstream tasks such as zero-shot image classification, text-to-image retrieval, and text-to-image generation while preserving task performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。