# Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA

arXiv: https://arxiv.org/abs/2512.12812 · HTML: https://mlsanity.com/paper/2512.12812/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Efficient Large Language Models: A Survey](https://mlsanity.com/paper/2312.03863/) (2023)
- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [Offline Reinforcement Learning for LLM Multi-Step Reasoning](https://mlsanity.com/paper/2412.16145/) (2024)
- [ComposerX: Multi-Agent Symbolic Music Composition with LLMs](https://mlsanity.com/paper/2404.18081/) (2024)
- [Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance](https://mlsanity.com/paper/2402.14531/) (2024)
- [Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformers](https://mlsanity.com/paper/2406.12199/) (2024)
- [CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models](https://mlsanity.com/paper/2509.09675/) (2025)
- [Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach](https://mlsanity.com/paper/2408.06634/) (2024)
- [Mitigating the Risk of Health Inequity Exacerbated by Large Language Models](https://mlsanity.com/paper/2410.05180/) (2024)
- [NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training](https://mlsanity.com/paper/2409.09582/) (2024)
- [Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification](https://mlsanity.com/paper/2509.26614/) (2025)
- [Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)](https://mlsanity.com/paper/2510.04950/) (2025)
- [Transformer-based Selective Super-Resolution for Efficient Image Refinement](https://mlsanity.com/paper/2312.05803/) (2023)
- [Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation](https://mlsanity.com/paper/2509.15772/) (2025)
- [Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs](https://mlsanity.com/paper/2506.12182/) (2025)
- [Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation](https://mlsanity.com/paper/2509.05746/) (2025)
- [Molecular Dynamics and Machine Learning Unlock Possibilities in Beauty Design -- A Perspective](https://mlsanity.com/paper/2410.18101/) (2024)
- [Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation](https://mlsanity.com/paper/2511.14271/) (2025)

## Built on by (most cited first, 23 of 23)

- [When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems](https://mlsanity.com/paper/2606.00448/) (2026)
- [Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models](https://mlsanity.com/paper/2603.21389/) (2026)
- [Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG](https://mlsanity.com/paper/2605.28044/) (2026)
- [Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance](https://mlsanity.com/paper/2606.00305/) (2026)
- [Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection](https://mlsanity.com/paper/2605.24834/) (2026)
- [OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention](https://mlsanity.com/paper/2602.05847/) (2026)
- [Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends](https://mlsanity.com/paper/2601.00536/) (2026)
- [Recursive Self-Evolving Agents via Held-Out Selection](https://mlsanity.com/paper/2606.28374/) (2026)
- [RoboRouter: Training-Free Policy Routing for Robotic Manipulation](https://mlsanity.com/paper/2603.07892/) (2026)
- [One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement](https://mlsanity.com/paper/2604.25444/) (2026)
- [ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2605.05126/) (2026)
- [Improving the Completeness and Comparability of Segment Disclosures: A Large Language Model Approach](https://mlsanity.com/paper/2605.23924/) (2026)
- [Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization](https://mlsanity.com/paper/2607.08057/) (2026)
- [A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges](https://mlsanity.com/paper/2602.05883/) (2026)
- [Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment](https://mlsanity.com/paper/2602.00531/) (2026)
- [Autonomous AI Agents for Option Hedging: Enhancing Financial Stability through Shortfall Aware Reinforcement Learning](https://mlsanity.com/paper/2603.06587/) (2026)
- [Unbiased Diffusion Variational Inversion via Principled Posterior Matching](https://mlsanity.com/paper/2605.25042/) (2026)
- [Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuits](https://mlsanity.com/paper/2605.30913/) (2026)
- [Evaluating and Understanding Model Editing for Medical Vision Language Models](https://mlsanity.com/paper/2607.05310/) (2026)
- [Understanding Tone-Dependent Inference Cost in Large Language Models](https://mlsanity.com/paper/2607.23915/) (2026)
- [MARS: Multi-Agent Re-ranking for Repeat-Order Food Delivery Recommendation](https://mlsanity.com/paper/2607.25420/) (2026)
- [Multimodal Plant Root Phenotyping with Integration of 3D Skeleton Extraction and Language Analysis](https://mlsanity.com/paper/2608.03109/) (2026)
- [Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs](https://mlsanity.com/paper/2610.01428/) (2026)

## Abstract (arXiv)

Prompt engineering has emerged as a critical factor influencing large language model (LLM) performance, yet the impact of pragmatic elements such as linguistic tone and politeness remains underexplored, particularly across different model families. In this work, we propose a systematic evaluation framework to examine how interaction tone affects model accuracy and apply it to three recently released and widely available LLMs: GPT-4o mini (OpenAI), Gemini 2.0 Flash (Google DeepMind), and Llama 4 Scout (Meta). Using the MMMLU benchmark, we evaluate model performance under Very Polite, Neutral, and Very Rude prompt variants across six tasks spanning STEM and Humanities domains, and analyze pairwise accuracy differences with statistical significance testing. Our results show that tone sensitivity is both model-dependent and domain-specific. Neutral or Very Polite prompts generally yield higher accuracy than Very Rude prompts, but statistically significant effects appear only in a subset of Humanities tasks, where rude tone reduces accuracy for GPT and Llama, while Gemini remains comparatively tone-insensitive. When performance is aggregated across tasks within each domain, tone effects diminish and largely lose statistical significance. Compared with earlier research, these findings suggest that dataset scale and coverage materially influence the detection of tone effects. Overall, our study indicates that while interaction tone can matter in specific interpretive settings, modern LLMs are broadly robust to tonal variation in typical mixed-domain use, providing practical guidance for prompt design and model selection in real-world deployments.