@inproceedings{jain-etal-2026-dissecting,
title = "Dissecting Transformers: A {CLEAR} Perspective Towards Green {AI}",
author = "Jain, Hemang and
Goyal, Shailender and
Pandey, Divyansh and
Vaidhyanathan, Karthik",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.21/",
pages = "452--483",
ISBN = "979-8-89176-459-0",
abstract = "The rapid adoption of Large Language Models (LLMs) has raised significant environmental concerns. Unlike the one-time cost of training, LLM inference occurs continuously and dominates the AI energy footprint. Yet most sustainability studies report only coarse model-level metrics, treating energy efficiency as an afterthought rather than a primary objective. Addressing the limitation, we propose Component-Level Energy Assessment via Repetitions (CLEAR), to overcome temporal mismatch between microsecond scale component execution and millisecond(ms) scale monitoring of energy sensors. Using CLEAR, we evaluate 15 models spanning four architecture types, keeping component-wise energy variance below 9.5{\%} while capturing over 90{\%} of total energy as individual components. We present the first comprehensive, fine-grained energy analysis of Transformer components across key parameters such as batch size, attention heads, hidden dimension, KV cache, and attention variants. Our findings reveal that Attention consumes significantly more Energy per FLOP as compared to the entire model, indicating that FLOPs alone fail to capture true component-level energy cost. CLEAR enables reliable fine-grained energy measurements and provides a strong formal foundation for predictive modelling of energy consumption."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jain-etal-2026-dissecting">
<titleInfo>
<title>Dissecting Transformers: A CLEAR Perspective Towards Green AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hemang</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shailender</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Divyansh</namePart>
<namePart type="family">Pandey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Vaidhyanathan</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>The rapid adoption of Large Language Models (LLMs) has raised significant environmental concerns. Unlike the one-time cost of training, LLM inference occurs continuously and dominates the AI energy footprint. Yet most sustainability studies report only coarse model-level metrics, treating energy efficiency as an afterthought rather than a primary objective. Addressing the limitation, we propose Component-Level Energy Assessment via Repetitions (CLEAR), to overcome temporal mismatch between microsecond scale component execution and millisecond(ms) scale monitoring of energy sensors. Using CLEAR, we evaluate 15 models spanning four architecture types, keeping component-wise energy variance below 9.5% while capturing over 90% of total energy as individual components. We present the first comprehensive, fine-grained energy analysis of Transformer components across key parameters such as batch size, attention heads, hidden dimension, KV cache, and attention variants. Our findings reveal that Attention consumes significantly more Energy per FLOP as compared to the entire model, indicating that FLOPs alone fail to capture true component-level energy cost. CLEAR enables reliable fine-grained energy measurements and provides a strong formal foundation for predictive modelling of energy consumption.</abstract>
<identifier type="citekey">jain-etal-2026-dissecting</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.21/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>452</start>
<end>483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dissecting Transformers: A CLEAR Perspective Towards Green AI
%A Jain, Hemang
%A Goyal, Shailender
%A Pandey, Divyansh
%A Vaidhyanathan, Karthik
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F jain-etal-2026-dissecting
%X The rapid adoption of Large Language Models (LLMs) has raised significant environmental concerns. Unlike the one-time cost of training, LLM inference occurs continuously and dominates the AI energy footprint. Yet most sustainability studies report only coarse model-level metrics, treating energy efficiency as an afterthought rather than a primary objective. Addressing the limitation, we propose Component-Level Energy Assessment via Repetitions (CLEAR), to overcome temporal mismatch between microsecond scale component execution and millisecond(ms) scale monitoring of energy sensors. Using CLEAR, we evaluate 15 models spanning four architecture types, keeping component-wise energy variance below 9.5% while capturing over 90% of total energy as individual components. We present the first comprehensive, fine-grained energy analysis of Transformer components across key parameters such as batch size, attention heads, hidden dimension, KV cache, and attention variants. Our findings reveal that Attention consumes significantly more Energy per FLOP as compared to the entire model, indicating that FLOPs alone fail to capture true component-level energy cost. CLEAR enables reliable fine-grained energy measurements and provides a strong formal foundation for predictive modelling of energy consumption.
%U https://aclanthology.org/2026.emnlp-main.21/
%P 452-483
Markdown (Informal)
[Dissecting Transformers: A CLEAR Perspective Towards Green AI](https://aclanthology.org/2026.emnlp-main.21/) (Jain et al., EMNLP 2026)
ACL
- Hemang Jain, Shailender Goyal, Divyansh Pandey, and Karthik Vaidhyanathan. 2026. Dissecting Transformers: A CLEAR Perspective Towards Green AI. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 452–483, Budapest, Hungary. Association for Computational Linguistics.