Cooking Up Politeness in Human-AI Information Seeking Dialogue

2026-01-14

AI Summary

This study investigates the impact of user politeness behaviors on the efficiency, information yield, and energy consumption of human–AI information-seeking dialogues. By annotating real-world conversations, clustering users, and simulating 18,000 cooking-assistance dialogues across three open-source large language models, the work systematically analyzes five distinct politeness styles. It reveals for the first time that politeness functions not merely as a social lubricant but significantly influences dialogue equity and computational energy efficiency: polite requests increase AI response length by 90% and information points by 38%, albeit at the cost of reduced information density; conversely, impolite inputs degrade energy efficiency, decreasing information per watt-hour by up to 48%. These findings highlight the hidden computational costs of politeness styles and offer a novel perspective for designing sustainable AI interactions.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Philosophy and Ethics of AI: Privacy & Security

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Politeness is a core dimension of human communication, yet its role in human-AI information seeking remains underexplored. We investigate how user politeness behaviour shapes conversational outcomes in a cooking-assistance setting. First, we annotated 30 dialogues, identifying four distinct user clusters ranging from Hyperpolite to Hyperefficient. We then scaled up to 18,000 simulated conversations across five politeness profiles (including impolite) and three open-weight models. Results show that politeness is not only cosmetic: it systematically affects response length, informational gain, and efficiency. Engagement-seeking prompts produced up to 90% longer replies and 38% more information nuggets than hyper-efficient prompts, but at markedly lower density. Impolite inputs yielded verbose but less efficient answers, with up to 48% fewer nuggets per watt-hour compared to polite input. These findings highlight politeness as both a fairness and sustainability issue: conversational styles can advantage or disadvantage users, and"polite"requests may carry hidden energy costs. We discuss implications for inclusive and resource-aware design of information agents.

Problem

• politeness
• human-AI dialogue
• information seeking
• conversational efficiency
• sustainability

Innovation

• politeness
• information-seeking dialogue
• conversational AI
• energy efficiency
• fairness