Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance

arXiv:2402.14531v1 Announce Type: new
Abstract: We investigate the impact of politeness levels in prompts on the performance of large language models (LLMs). Polite language in human communications often garners more compliance and effectiveness, while rudeness can cause aversion, impacting response quality. We consider that LLMs mirror human communication traits, suggesting they align with human cultural norms. We assess the impact of politeness in prompts on LLMs across English, Chinese, and Japanese tasks. We observed that impolite prompts often result in …

abstract arxiv communications compliance cross-lingual cs.cl human impact influence language language models large language large language models llm llm performance llms performance prompt prompts quality study type