Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles 事件

Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles arXiv:2606.12088v1 Announce Type: new Abstract: Most fairness research in NLP assumes direct access to protected attributes such as gender, race, or nationality. In practice, however, such information is often unavailable due to privacy constraints, missing metadata, or legal restrictions, even though models may infer it from indirect textual cues. This raises a key question: can debiasing succeed without direc