@inproceedings{bao-etal-2026-energy,
title = "The Energy Footprint of {LLM}-Based Environmental Analysis: {LLM}s and Domain Products",
author = "Bao, Alicia and
Hsu, Angel and
Manya, Diego and
Zhang, Ji and
He, Jiamian",
editor = "Schimanski, Tobias and
Usmanova, Aida and
Morio, Gaku and
Ni, Jingwei and
Dutia, Kalyan and
Vaghefi, Seyed Saeid and
Stammbach, Dominik and
Leippold, Markus",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change ({C}limate{NLP} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.climatenlp-1.16/",
pages = "220--230",
ISBN = "979-8-89176-465-1",
abstract = "As large language models (LLMs) are increasingly used, understanding their energy footprint has become an important concern. The growing adoption of retrieval-augmented (RAG) based pipelines for climate-domain specific analysis raises a key question: how does the energy consumption of domain-specific RAG-based pipelines compare with that of direct generic LLM usage? Prior research has focused on standalone model calls or coarse token-based estimates, while leaving the energy implications of deployed application workflows insufficiently understood. In this paper, we assess the inference-time energy consumption of two LLM-based climate analysis chatbots (ChatNetZero and ChatNDC) compared to the generic GPT-4o-mini model. We estimate energy use under actual user queries by decomposing each workflow into retrieval, generation, and hallucination-checking components. We also test across different times of day and geographic access locations. Our results show that the energy consumption of domain-specific RAG-based pipelines depends strongly on their design. More agentic pipelines substantially increase inference-time energy use, particularly when used for additional accuracy or verification checks, although they may not yield proportional gains in response quality. This study provides a new understanding on how the design of domain-specific LLM products affects both the energy footprint and quality of output."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2026-energy">
<titleInfo>
<title>The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angel</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Manya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiamian</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Schimanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Usmanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalyan</namePart>
<namePart type="family">Dutia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Saeid</namePart>
<namePart type="family">Vaghefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Stammbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Leippold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-465-1</identifier>
</relatedItem>
<abstract>As large language models (LLMs) are increasingly used, understanding their energy footprint has become an important concern. The growing adoption of retrieval-augmented (RAG) based pipelines for climate-domain specific analysis raises a key question: how does the energy consumption of domain-specific RAG-based pipelines compare with that of direct generic LLM usage? Prior research has focused on standalone model calls or coarse token-based estimates, while leaving the energy implications of deployed application workflows insufficiently understood. In this paper, we assess the inference-time energy consumption of two LLM-based climate analysis chatbots (ChatNetZero and ChatNDC) compared to the generic GPT-4o-mini model. We estimate energy use under actual user queries by decomposing each workflow into retrieval, generation, and hallucination-checking components. We also test across different times of day and geographic access locations. Our results show that the energy consumption of domain-specific RAG-based pipelines depends strongly on their design. More agentic pipelines substantially increase inference-time energy use, particularly when used for additional accuracy or verification checks, although they may not yield proportional gains in response quality. This study provides a new understanding on how the design of domain-specific LLM products affects both the energy footprint and quality of output.</abstract>
<identifier type="citekey">bao-etal-2026-energy</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.16/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>220</start>
<end>230</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products
%A Bao, Alicia
%A Hsu, Angel
%A Manya, Diego
%A Zhang, Ji
%A He, Jiamian
%Y Schimanski, Tobias
%Y Usmanova, Aida
%Y Morio, Gaku
%Y Ni, Jingwei
%Y Dutia, Kalyan
%Y Vaghefi, Seyed Saeid
%Y Stammbach, Dominik
%Y Leippold, Markus
%S Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-465-1
%F bao-etal-2026-energy
%X As large language models (LLMs) are increasingly used, understanding their energy footprint has become an important concern. The growing adoption of retrieval-augmented (RAG) based pipelines for climate-domain specific analysis raises a key question: how does the energy consumption of domain-specific RAG-based pipelines compare with that of direct generic LLM usage? Prior research has focused on standalone model calls or coarse token-based estimates, while leaving the energy implications of deployed application workflows insufficiently understood. In this paper, we assess the inference-time energy consumption of two LLM-based climate analysis chatbots (ChatNetZero and ChatNDC) compared to the generic GPT-4o-mini model. We estimate energy use under actual user queries by decomposing each workflow into retrieval, generation, and hallucination-checking components. We also test across different times of day and geographic access locations. Our results show that the energy consumption of domain-specific RAG-based pipelines depends strongly on their design. More agentic pipelines substantially increase inference-time energy use, particularly when used for additional accuracy or verification checks, although they may not yield proportional gains in response quality. This study provides a new understanding on how the design of domain-specific LLM products affects both the energy footprint and quality of output.
%U https://aclanthology.org/2026.climatenlp-1.16/
%P 220-230
Markdown (Informal)
[The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products](https://aclanthology.org/2026.climatenlp-1.16/) (Bao et al., ClimateNLP 2026)
ACL