<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="politov-etal-2026-energy">
    <titleInfo>
        <title>Energy-Aware Benchmarking of Generative Information Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andrei</namePart>
        <namePart type="family">Politov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Iryna</namePart>
        <namePart type="family">Vergunova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rene</namePart>
        <namePart type="family">Jäkel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Färber</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Using Large Language Models (LLMs) for Information Extraction (IE) inherently involves transforming diverse textual inputs into strictly formatted outputs. Guaranteeing this structural validity introduces a hidden energy tax driven by constrained decoding mechanisms, serialisation formats, and underlying serving configurations. Consequently, standard token-level metrics fail to capture the true energy cost of generative IE, which also cannot be predicted by model size alone. To address this, we introduce the first dedicated benchmark evaluating the energy-accuracy trade-offs of generative IE. Our framework establishes task-aligned energy metrics, including Energy per True Positive (J/TP) and the F1-Energy Ratio (F₁/kJ). Through comprehensive ablation across architectures, decoding regimes, and serving-layer limits, we demonstrate that efficiency is governed by complex parameter interactions. We translate these findings into actionable configuration guidelines, equipping practitioners to maximise predictive accuracy, optimise energy yield, or achieve a sustainable Pareto balance.</abstract>
    <identifier type="citekey">politov-etal-2026-energy</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2002/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>42668</start>
            <end>42691</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Energy-Aware Benchmarking of Generative Information Extraction
%A Politov, Andrei
%A Vergunova, Iryna
%A Jäkel, Rene
%A Färber, Michael
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F politov-etal-2026-energy
%X Using Large Language Models (LLMs) for Information Extraction (IE) inherently involves transforming diverse textual inputs into strictly formatted outputs. Guaranteeing this structural validity introduces a hidden energy tax driven by constrained decoding mechanisms, serialisation formats, and underlying serving configurations. Consequently, standard token-level metrics fail to capture the true energy cost of generative IE, which also cannot be predicted by model size alone. To address this, we introduce the first dedicated benchmark evaluating the energy-accuracy trade-offs of generative IE. Our framework establishes task-aligned energy metrics, including Energy per True Positive (J/TP) and the F1-Energy Ratio (F₁/kJ). Through comprehensive ablation across architectures, decoding regimes, and serving-layer limits, we demonstrate that efficiency is governed by complex parameter interactions. We translate these findings into actionable configuration guidelines, equipping practitioners to maximise predictive accuracy, optimise energy yield, or achieve a sustainable Pareto balance.
%U https://aclanthology.org/2026.findings-emnlp.2002/
%P 42668-42691

Markdown (Informal)

[Energy-Aware Benchmarking of Generative Information Extraction](https://aclanthology.org/2026.findings-emnlp.2002/) (Politov et al., Findings 2026)

• Energy-Aware Benchmarking of Generative Information Extraction (Politov et al., Findings 2026)

ACL

• Andrei Politov, Iryna Vergunova, Rene Jäkel, and Michael Färber. 2026. Energy-Aware Benchmarking of Generative Information Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 42668–42691, Budapest, Hungary. Association for Computational Linguistics.