Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Understanding Tone-Dependent Inference Cost in Large Language Models
Akhil Kumar, Om Dobariya
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-…
cs.CL2025
Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)
Om Dobariya, Akhil Kumar
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 t…