conftrace_

controllable debiasing

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

pre-trained language model (2) bias mitigation (2) conceptual shortcut (1) unsupervised revision (1) connotation frame (1) gate adapter (1) fairness list-wise regularization (1) text debiasing (1) biased language (1) adversarial debiasing (1)

Papers

CURE: Controlled Unlearning for Robust Embeddings — Mitigating Conceptual Shortcuts in Pre-Trained Language Models EMNLP 2025 Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters EACL 2024 PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction EMNLP 2020