mlsanityData to 14 Oct 2026

Understanding Tone-Dependent Inference Cost in Large Language Models

arXiv 2607.23915 ↗First posted 27 Jul 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We examine how prompt tone affects both accuracy of the LLM answers and inference cost as reflected in output-token consumption. Experiments were performed to understand the trade-offs between accuracy and inference cost on a 570 Question MMLU dataset for LLM models prompted in seven different tones from sycophantic to threatening. Our results show that the output-token-length variation substantially exceeded accuracy variation across all models. Output-token consumption varied by up to 44.3% across tone conditions. We also analyzed the tradeoff between the accuracy of the answers and the average output token length in the reasoning process. For the ChatGPT models 4o and 5-nano, the rude tone is quite dominant. For the Gemini models 2.5 Flash and 2.5 Flash Lite, the rude and neutral tones are dominant on the Pareto-optimal frontier. We find that prompt tone influences not only answer quality but also the amount of billable inference resources consumed by modern LLMs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 18 references that are in the map. First posted on arXiv 27 Jul 2026.

Builds on

13 of 18 references.

References · 13

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  5. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 570
  6. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  7. 2025Prompt Repetition Improves Non-Reasoning LLMscited by 27
  8. 2023Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Modelscited by 24
  9. 2024Open (Clinical) LLMs are Sensitive to Instruction Phrasingscited by 24
  10. 2025Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMAcited by 23
  11. 2025Prompting Science Report 1: Prompt Engineering is Complicated and Contingentcited by 8
  12. 2025Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)cited by 8
1 more
  1. 2026Small Talk, Big Impact: The Energy Cost of Thanking AIcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost
  2. 2025An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint
  3. 2025Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
  4. 2026A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality
  5. 2026Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference
  6. 2023Batch Prompting: Efficient Inference with Large Language Model APIs
  7. 2026Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations
  8. 2025High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning