How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
arXiv:2610.11005v1 Announce Type: new Abstract: Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper. We measure this vulnerability across...
Read more: https://arxiv.org/abs/2610.11005
Scan with your phone
Scan with your phone