Politeness to ChatGPT Reconsidered: Structural Injustice and Respect for Rational Agents

Abstract

The widespread interaction between humans and large language models has sparked normative debates regarding user politeness toward artificial intelligence. This paper explores the ethical rationality of maintaining polite linguistic norms in human-LLM interaction, arguing against the normative obligation of being polite to artificial intelligence. It analyzes the social risks triggered by normalized AI politeness, demonstrating that such social norms drive technology enterprises to form fixed politeness-conditioned design under the constraint of AI value alignment mechanisms. This design centered on English cultural logic leads to differential algorithmic treatment of users from diverse cultural, linguistic and physical ability backgrounds, resulting in structural social injustice. From the perspective of Kantian moral philosophy and capability ethics, this study verifies that the algorithmic differential treatment essentially disrespects human rational agency and erodes individual autonomous capacities. The research concludes that practicing politeness toward large language models is ethically inappropriate due to its inherent injustice, and such interactive norms should not be universally advocated.