Paper recorded by Signals 4 on 2026-10-22 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-22 on arXiv · recorded by Signals 4 on 2026-10-23
Category: cs.AI · 人工智能 · first seen 2026-10-23
Control evaluations measure whether safeguards can prevent an AI model from causing undesired outcomes even when it is intentionally trying to do so. These evaluations typically use purpose-built control settings and extrapolate their results to a model's deployment. However, the effectiveness of safeguards in deployment can depend on features of environments and tasks that control settings do not