Salvato in:
Dettagli Bibliografici
Autori principali: Delavande, Julien, Pierrard, Regis, Luccioni, Sasha
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.22357
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911408645472256
author Delavande, Julien
Pierrard, Regis
Luccioni, Sasha
author_facet Delavande, Julien
Pierrard, Regis
Luccioni, Sasha
contents Being polite is free - or is it? In this paper, we quantify the energy cost of seemingly innocuous messages such as ``thank you'' when interacting with large language models, often used by users to convey politeness. Using real-world conversation traces and fine-grained energy measurements, we quantify how input length, output length and model size affect energy use. While politeness is our motivating example, it also serves as a controlled and reproducible proxy for measuring the energy footprint of a typical LLM interaction. Our findings provide actionable insights for building more sustainable and efficient LLM applications, especially in increasingly widespread real-world contexts like chat. As user adoption grows and billions of prompts are processed daily, understanding and mitigating this cost becomes crucial - not just for efficiency, but for sustainable AI deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22357
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Small Talk, Big Impact: The Energy Cost of Thanking AI
Delavande, Julien
Pierrard, Regis
Luccioni, Sasha
Machine Learning
Being polite is free - or is it? In this paper, we quantify the energy cost of seemingly innocuous messages such as ``thank you'' when interacting with large language models, often used by users to convey politeness. Using real-world conversation traces and fine-grained energy measurements, we quantify how input length, output length and model size affect energy use. While politeness is our motivating example, it also serves as a controlled and reproducible proxy for measuring the energy footprint of a typical LLM interaction. Our findings provide actionable insights for building more sustainable and efficient LLM applications, especially in increasingly widespread real-world contexts like chat. As user adoption grows and billions of prompts are processed daily, understanding and mitigating this cost becomes crucial - not just for efficiency, but for sustainable AI deployment.
title Small Talk, Big Impact: The Energy Cost of Thanking AI
topic Machine Learning
url https://arxiv.org/abs/2601.22357