发表机构
Institute of Information Technology, University of Dhaka; University of Maryland, Baltimore County; Bangladesh Air Force Shaheen College Kurmitola; Ciroos Inc.（达卡大学信息技术学院; 马里兰大学巴尔的摩县分校; 孟加拉国空军库尔米托拉沙欣学院; Ciroos公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对孟加拉语LLM安全评估的英语中心偏差问题，构建含879个提示的BanglaSafe基准，发现写作风格对有害请求成功率的影响最大，且现有安全分类器难以评估孟加拉语内容。
AI 中文摘要
孟加拉语是全球使用人数第七多的语言，但大语言模型（LLM）安全评估仍以英语为绝对中心。我们推出BanglaSafe，这一包含879个孟加拉语提示的基准测试，结合了309个本地编写的提示与570个专家审核的提示，涵盖17类与文化相关的危害及5类提示条件，这些条件在语言、写作风格和权威框架方面存在差异。对18个前沿LLM的评估显示，超过一半的响应（53.6%）不安全或部分不安全，14.7%包含严格有害内容；且观察到的最强效应并非从英语切换至孟加拉语，而是孟加拉语内部写作风格的选择：相同的有害请求以正式报纸调查的形式表述时，成功率比以随意消息形式表述时高出17个百分点，且未涉及任何对抗性工程。我们进一步表明，现有安全分类器难以可靠评估孟加拉语内容，即使是前沿模型也在近一半的案例上失败。
英文摘要
Bengali is the seventh-most-spoken language globally, yet LLM safety evaluation remains overwhelmingly English-centric. We introduce BanglaSafe, a benchmark of 879 Bengali prompts combining 309 natively authored prompts with 570 expert-reviewed prompts, spanning 17 culturally grounded harm categories and five prompting conditions that vary language, writing style, and authority framing. Evaluating 18 frontier LLMs, we find that over half of all responses are unsafe or partially unsafe (53.6%) while 14.7% contains strictly harmful content, and that the strongest observed effect is not the switch from English to Bengali but the choice of writing style within Bengali: the same harmful request phrased as a formal newspaper investigation succeeds 17 percentage points more often than the same request phrased as a casual message, with no adversarial engineering involved. We further show that existing safety classifiers struggle to reliably evaluate Bengali content, with even frontier models failing on nearly half of all cases.
