Gender bias and factual gender knowledge are severely entangled in language model circuits and neurons, making neuron ablation an unreliable method for debiasing.
Dissect- ing bias in llms: A mechanistic interpretability perspective
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Implicit generative choices in diffusion models concentrate in self-attention layers; targeted ICM interventions there outperform broader debiasing methods with fewer artifacts.
citing papers explorer
-
GKnow: Measuring the Entanglement of Gender Bias and Factual Gender
Gender bias and factual gender knowledge are severely entangled in language model circuits and neurons, making neuron ablation an unreliable method for debiasing.
-
Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
Implicit generative choices in diffusion models concentrate in self-attention layers; targeted ICM interventions there outperform broader debiasing methods with fewer artifacts.