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
PrivacySkills is introduced, a controlled framework for evaluating how agents choose among acquisition pathways that provide the same task-relevant value: consulting publicly available personal information, accessing confidential sources, or interacting with the user.
Lucas Biechy, Cédric Eichler, H. H. Arcolezi et al.· 0 citations
While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces systemic overconfidence. In production environments, where logits may be unavailable, robust black-box uncertainty quantification (UQ) is essential for trustworthiness and safety. Focusing on question-...
Lucas Biechy, Cédric Eichler, Adrien Boiret et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.