标题为英语How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
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 languages and registers: attack success on Qwen3-1.7B is already 89.4% in English and 93.0% in…
AI 摘要：要点
- 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 languages and registers: attack success on Qwen3-1.7B is already 89.4% in English and 93.0% in…
How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
相关文章
法官驳回萨姆·奥尔特曼妹妹的性虐待诉讼
周二，美国地区法官 Zachary Bluestone 驳回了 Ann Altman 去年提起的诉讼，指控她的兄弟、OpenAI 首席执行官 Sam Altman 在她的整个童年时期对她进行了性虐待。正如《卫报》早些时候报道的那样，法官写道，去年，安……
ENAnthropic pitches AI safety bill that may block a model if 50+ people could be killed
The proposed policy seems to offer protections against AI run amok but actually forbids federal agencies from blocking a model's release without the permission of a judge.
ENHugging Face CEO warns that Netflix’s OpenAI hack documentary isn’t accurate
Before you share the Netflix documentary "AI Gone Rogue" take note. Clem Delangue, Hugging Face's co-founder who is featured in the film, says it went "full doomer mode" and isn't accurate.
ENAnthropic’s cloud partnerships are getting messy
Anthropic is reportedly struggling to secure enough compute from cloud providers that increasingly view it as a competitor, even as its infrastructure spending balloons ahead of a planned November IPO.