Newest papers

Rethinking Post-hoc Debiasing of Large Pretrained Models

Divyaansh Mertia, Chirag Bhutra, Himanshu Shekhar, Shubham Bagwari, Pratik Mazumder · 2026 · arXiv

DOI: 10.48550/arXiv.2610.29688 · open-access PDF

Chinese

像CLIP这样的大型预训练模型被广泛用作冷冻特征提取器。然而,他们的嵌入从训练数据中继承了错误的相关性,引入了偏见的特征。越来越多的研究人员试图通过后期偏差来解决这个问题,使脊椎不受影响。我们发现,尽管有不同的机制,这些方法需要偏见特征在文本中被识别和表达。这种依赖并非无害。

Machine translation (Meta M2M100); the English original follows.

Abstract

Large pretrained models such as CLIP are widely used as frozen feature extractors. However, their embeddings inherit spurious correlations from training data, introducing bias into the features. A growing body of research has sought to address this issue through post hoc debiasing, leaving the backbone untouched. We discover that despite differing mechanisms, these methods require the bias feature to be identified and expressed in text. This dependency is not innocuous. In this work, we experimentally demonstrate that this requirement incurs an unforeseen penalty in certain scenarios. For exam

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange