Paper recorded by Signals 4 on 2026-10-05 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-05 on arXiv · recorded by Signals 4 on 2026-10-06
Category: cs.CL · 自然语言处理 · first seen 2026-10-06
Are language models compliant with user instructions? A model that always complies can be stopped but also exploited, while one that always resists can be neither exploited nor stopped. We contribute an open two-probe benchmark that can place any language model on this spectrum. In the active probe, a user instructs the model to act and accept a lower payoff, which measures exploitability. In the