Benchmarking the Energy Savings with Speculative Decoding Strategies

Rohit Dutta; Paramita Koley; Soham Poddar; Janardan Misra; Sanjay Podder; Naveen Balani; Saptarshi Ghosh; Niloy Ganguly

Benchmarking the Energy Savings with Speculative Decoding Strategies

Rohit Dutta, Paramita Koley, Soham Poddar, Janardan Misra, Sanjay Podder, Naveen Balani, Saptarshi Ghosh, Niloy Ganguly

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper presents a comprehensive survey of energy requirements of speculative decoding strategies, with detailed analysis on how various factors – model size and family, speculative decoding strategies, and dataset characteristics – influence the energy optimizations.

Anthology ID:: 2026.findings-eacl.249
Volume:: Findings of the Association for Computational Linguistics: EACL 2026
Month:: March
Year:: 2026
Address:: Rabat, Morocco
Editors:: Vera Demberg, Kentaro Inui, Lluís Marquez
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 4737–4748
Language:
URL:: https://aclanthology.org/2026.findings-eacl.249/
DOI:
Bibkey:
Cite (ACL):: Rohit Dutta, Paramita Koley, Soham Poddar, Janardan Misra, Sanjay Podder, Naveen Balani, Saptarshi Ghosh, and Niloy Ganguly. 2026. Benchmarking the Energy Savings with Speculative Decoding Strategies. In Findings of the Association for Computational Linguistics: EACL 2026, pages 4737–4748, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):: Benchmarking the Energy Savings with Speculative Decoding Strategies (Dutta et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-eacl.249.pdf
Checklist:: 2026.findings-eacl.249.checklist.pdf

PDF Cite Search Checklist Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{dutta-etal-2026-benchmarking,
    title = "Benchmarking the Energy Savings with Speculative Decoding Strategies",
    author = "Dutta, Rohit  and
      Koley, Paramita  and
      Poddar, Soham  and
      Misra, Janardan  and
      Podder, Sanjay  and
      Balani, Naveen  and
      Ghosh, Saptarshi  and
      Ganguly, Niloy",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-eacl.249/",
    pages = "4737--4748",
    ISBN = "979-8-89176-386-9",
    abstract = "Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper presents a comprehensive survey of energy requirements of speculative decoding strategies, with detailed analysis on how various factors {--} model size and family, speculative decoding strategies, and dataset characteristics {--} influence the energy optimizations."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dutta-etal-2026-benchmarking">
    <titleInfo>
        <title>Benchmarking the Energy Savings with Speculative Decoding Strategies</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rohit</namePart>
        <namePart type="family">Dutta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paramita</namePart>
        <namePart type="family">Koley</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Soham</namePart>
        <namePart type="family">Poddar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Janardan</namePart>
        <namePart type="family">Misra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sanjay</namePart>
        <namePart type="family">Podder</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Naveen</namePart>
        <namePart type="family">Balani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saptarshi</namePart>
        <namePart type="family">Ghosh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Niloy</namePart>
        <namePart type="family">Ganguly</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper presents a comprehensive survey of energy requirements of speculative decoding strategies, with detailed analysis on how various factors – model size and family, speculative decoding strategies, and dataset characteristics – influence the energy optimizations.</abstract>
    <identifier type="citekey">dutta-etal-2026-benchmarking</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.249/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>4737</start>
            <end>4748</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Benchmarking the Energy Savings with Speculative Decoding Strategies
%A Dutta, Rohit
%A Koley, Paramita
%A Poddar, Soham
%A Misra, Janardan
%A Podder, Sanjay
%A Balani, Naveen
%A Ghosh, Saptarshi
%A Ganguly, Niloy
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F dutta-etal-2026-benchmarking
%X Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper presents a comprehensive survey of energy requirements of speculative decoding strategies, with detailed analysis on how various factors – model size and family, speculative decoding strategies, and dataset characteristics – influence the energy optimizations.
%U https://aclanthology.org/2026.findings-eacl.249/
%P 4737-4748

Download as File

Markdown (Informal)

[Benchmarking the Energy Savings with Speculative Decoding Strategies](https://aclanthology.org/2026.findings-eacl.249/) (Dutta et al., Findings 2026)

Benchmarking the Energy Savings with Speculative Decoding Strategies (Dutta et al., Findings 2026)

ACL

Rohit Dutta, Paramita Koley, Soham Poddar, Janardan Misra, Sanjay Podder, Naveen Balani, Saptarshi Ghosh, and Niloy Ganguly. 2026. Benchmarking the Energy Savings with Speculative Decoding Strategies. In Findings of the Association for Computational Linguistics: EACL 2026, pages 4737–4748, Rabat, Morocco. Association for Computational Linguistics.