No Universal Courtesy: A Cross-Linguistic, Multi-Model Study of Politeness Effects on LLMs Using the PLUM Corpus
arXiv:2604.16275v1 Announce Type: new
Abstract: This paper explores the response of Large Language Models (LLMs) to user prompts with different degrees of politeness and impoliteness. The Politeness Theory by Brown and Levinson and the Impoliteness Fr…