Debiasing language-model training data for a target group frequently increases stereotyping or counter-stereotyping for non-target groups across categories, models, and scales.
Debiasing Pretrained Text Encoders by Paying Attention to Paying Attention
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
LLMs contain identifiable COCO neurons that enable implicit self-correction against stereotypes; targeted editing of these neurons improves fairness and robustness to jailbreaks while preserving generation quality.
citing papers explorer
-
When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation
Debiasing language-model training data for a target group frequently increases stereotyping or counter-stereotyping for non-target groups across categories, models, and scales.
-
Modeling Implicit Conflict Monitoring Mechanisms against Stereotypes in LLMs
LLMs contain identifiable COCO neurons that enable implicit self-correction against stereotypes; targeted editing of these neurons improves fairness and robustness to jailbreaks while preserving generation quality.