Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)

View PDF Abstract:The wording of natural language prompts has been shown to influence the performance of large language models (LLMs), yet the role of politeness and tone remains underexplored. In this study, we investigate how varying levels of prompt politeness affect model accuracy on multiple-choice questions. We created a dataset of 50 base questions spanning mathematics, science, and history, each rewritten into five tone variants: Very Polite, Polite, Neutral, Rude, and Very Rude, yielding 250 unique prompts. Using ChatGPT 4o, we evaluated responses across these conditions and applied paired sample t-tests to assess statistical significance. Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. These findings differ from earlier studies that associated rudeness with poorer outcomes, suggesting that newer LLMs may respond differently to tonal variation. Our results highlight the importance of studying pragmatic aspects of prompting and raise broader questions about the social dimensions of human-AI interaction.

Comments: 5 pages, 3 tables; includes Limitations and Ethical Considerations sections; short paper under submission to Findings of ACL 2025

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Methodology (stat.ME) Cite as: arXiv:2510.04950 [cs.CL]   (or arXiv:2510.04950v1 [cs.

CL] for this version)   https://doi.org/10.48550/arXiv.2510.04950 arXiv-issued DOI via DataCite Submission history From: Om Dobariya [view email] [v1] Mon, 6 Oct 2025 15:50:39 UTC (337 KB)