Реклама

Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation

#LLMs #Safe #Beyond #Text #Emojis

arXiv:2608.18164v1 Announce Type: new Abstract: Safety evaluations of large language models (LLMs) predominantly rely on text-based adversarial prompts, potentially overlooking vulnerabilities arising from alternative input representations. This work examines emoji-augmented prompts as a test case…