From Observation to Intervention: Identifiability of Latent User Bias in Human-AI Interaction
This paper formalizes when an AI system can distinguish true user preferences from behavior shaped by cognitive bias, and proves that an Observer applying a finite sequence of adversarial zero-reward interventions of length $m_\delta$ makes the post-intervention action distributions arbitrarily separable.
Lucas Biechy, Yuxuan Li, Zhonghao He et al.
· 0 citations