IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks

תקציר מקורי באנגליתarXiv:2609.03781v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in multilingual settings, yet their safety is still evaluated primarily in English. This limits our understanding of how alignment failures manifest in low-resource and culturally diverse languages. We introduce IndicSafeEval, a persuasion-based jailbreak evaluation framework for Indian languages. Our benchmark combines ten safety critical content categories with six human-like persuasive strategies across four different Indian languages, such as Hindi, Bengali, Marathi and Punjabi, resulting in 7,200 adversarial prompts. We conduct a systematic black-box evaluation of several open-source LLMs to examine how their safety behaviour varies across languages, persuasion strategies, and risk categ