כיצד קיפול סיפורי משפיל את LLM: מבחן והגנה בשפות שונות

תקציר מקורי באנגליתarXiv: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 languages and registers: attack success on Qwen3-1.7B is already 89.4% in English and 93.0% in modern Chinese, and reaches 95.7% in Classical Chinese. We build GUISE, a benchmark for systematically studying this vulnerability. It includes parallel requests in English, modern Chinese, and Classical Chinese, matched harmful and benign pairs, wrapper types held out for evaluation, and a stricter criterion that counts warn-then-answer responses as attack successes. Representation analysis shows that language and register move harmful-request representations only sli