conftrace_

bias formation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sycophantic confabulation (1) geometric manifold analysis (1) bias dynamics (1) large language model (1) activation steering (1) spurious feature (1) teacher-student setup (1) sparse autoencoder (1) sgd dynamics (1) gaussian mixture model (1)

Papers

Probing Bias Formation in Medical LLMs through Activation Steering ACL 2026 Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training NeurIPS 2024