# Comparing human and LLM politeness strategies in free production

arXiv: https://arxiv.org/abs/2506.09391 · HTML: https://mlsanity.com/paper/2506.09391/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2025.

## Built on by (most cited first, 9 of 9)

- [Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs](https://mlsanity.com/paper/2601.04435/) (2026)
- [AI Assistance Reduces Persistence and Hurts Independent Performance](https://mlsanity.com/paper/2604.04721/) (2026)
- [On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts](https://mlsanity.com/paper/2509.06952/) (2025)
- [Cognitive models can reveal interpretable value trade-offs in language models](https://mlsanity.com/paper/2506.20666/) (2025)
- [Affective Context Amplifies Sycophancy in LLM Responses](https://mlsanity.com/paper/2608.21242/) (2026)
- [Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild](https://mlsanity.com/paper/2605.05767/) (2026)
- [No Universal Courtesy: A Cross-Linguistic, Multi-Model Study of Politeness Effects on LLMs Using the PLUM Corpus](https://mlsanity.com/paper/2604.16275/) (2026)
- [Polite but Misaligned: Evaluating LLM Politeness Judgments Against Human Pragmatic Norms](https://mlsanity.com/paper/2609.29001/) (2026)
- [CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges](https://mlsanity.com/paper/2610.02622/) (2026)

## Abstract (arXiv)

Polite speech poses a fundamental alignment challenge for large language models (LLMs). Humans deploy a rich repertoire of linguistic strategies to balance informational and social goals -- from positive approaches that build rapport (compliments, expressions of interest) to negative strategies that minimize imposition (hedging, indirectness). We investigate whether LLMs employ a similarly context-sensitive repertoire by comparing human and LLM responses in both constrained and open-ended production tasks. We find that larger models (≥70B parameters) successfully replicate key preferences from the computational pragmatics literature, and human evaluators surprisingly prefer LLM-generated responses in open-ended contexts. However, further linguistic analyses reveal that models disproportionately rely on negative politeness strategies even in positive contexts, potentially leading to misinterpretations. While modern LLMs demonstrate an impressive handle on politeness strategies, these subtle differences raise important questions about pragmatic alignment in AI systems.