Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models 文章

ArXiv CS.AI2026-06-09NEWSen作者: Arya Shah, Himanshu Beniwal, Mayank Singh, Chaklam Silpasuwanchai

Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models · 相关技术

暂无数据