Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents

arXiv:2610.28982v1 Announce Type: new Abstract: While large language models are increasingly deployed as tool-calling agents, their safety evaluations still focus primarily on their ability to refuse harmful requests in text. We investigate whether the refusal behavior in text transfers to tool use.

arXiv cs.AIDonnerstag 06:00 · 22.10.1 Min. Lesezeit