@inproceedings{marmol-romero-etal-2026-introducing,
title = "Introducing a Green Leaderboard for Sustainable Risk Prediction in Streaming {NLP} Shared Tasks.",
author = "M{\'a}rmol-Romero, Alba Mar{\'i}a and
Moreno Mu{\~n}oz, Adri{\'a}n and
Montejo-Raez, Arturo",
editor = "Grasso, Francesca and
Basile, Valerio and
Bosco, Cristina and
Ibrohim, Muhammad Okky and
Skeppstedt, Maria and
Stede, Manfred",
booktitle = "Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2026.nlp4ecology-1.13/",
doi = "10.63317/3cbext6ixjh2",
pages = "144--153",
abstract = "Current NLP shared-task evaluations predominantly rank systems by predictive performance, overlooking computational efficiency and environmental impact. This limitation is particularly critical in streaming and early risk detection scenarios, where models operate continuously, and resource consumption accumulates over time. We propose a sustainability-aware evaluation framework for streaming NLP tasks by introducing the Green Early Detection Score (GED), which integrates classification performance, detection timeliness, and carbon emissions. We also present an energy-based variant tailored to on-device early risk detection settings where energy consumption per inference is a key constraint. Applying these metrics to three editions (2023-2025) of the MentalRiskES shared task, we construct the first Green Leaderboard for early risk detection. Our results show that sustainability-aware ranking substantially reshapes system positions, highlighting efficient models that remain undervalued under performance-only evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marmol-romero-etal-2026-introducing">
<titleInfo>
<title>Introducing a Green Leaderboard for Sustainable Risk Prediction in Streaming NLP Shared Tasks.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alba</namePart>
<namePart type="given">María</namePart>
<namePart type="family">Mármol-Romero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrián</namePart>
<namePart type="family">Moreno Muñoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Grasso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Bosco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Okky</namePart>
<namePart type="family">Ibrohim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Skeppstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current NLP shared-task evaluations predominantly rank systems by predictive performance, overlooking computational efficiency and environmental impact. This limitation is particularly critical in streaming and early risk detection scenarios, where models operate continuously, and resource consumption accumulates over time. We propose a sustainability-aware evaluation framework for streaming NLP tasks by introducing the Green Early Detection Score (GED), which integrates classification performance, detection timeliness, and carbon emissions. We also present an energy-based variant tailored to on-device early risk detection settings where energy consumption per inference is a key constraint. Applying these metrics to three editions (2023-2025) of the MentalRiskES shared task, we construct the first Green Leaderboard for early risk detection. Our results show that sustainability-aware ranking substantially reshapes system positions, highlighting efficient models that remain undervalued under performance-only evaluation.</abstract>
<identifier type="citekey">marmol-romero-etal-2026-introducing</identifier>
<identifier type="doi">10.63317/3cbext6ixjh2</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4ecology-1.13/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>144</start>
<end>153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing a Green Leaderboard for Sustainable Risk Prediction in Streaming NLP Shared Tasks.
%A Mármol-Romero, Alba María
%A Moreno Muñoz, Adrián
%A Montejo-Raez, Arturo
%Y Grasso, Francesca
%Y Basile, Valerio
%Y Bosco, Cristina
%Y Ibrohim, Muhammad Okky
%Y Skeppstedt, Maria
%Y Stede, Manfred
%S Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing
%D 2026
%8 May
%I European Language Resources Association
%C Palma de Mallorca, Spain
%F marmol-romero-etal-2026-introducing
%X Current NLP shared-task evaluations predominantly rank systems by predictive performance, overlooking computational efficiency and environmental impact. This limitation is particularly critical in streaming and early risk detection scenarios, where models operate continuously, and resource consumption accumulates over time. We propose a sustainability-aware evaluation framework for streaming NLP tasks by introducing the Green Early Detection Score (GED), which integrates classification performance, detection timeliness, and carbon emissions. We also present an energy-based variant tailored to on-device early risk detection settings where energy consumption per inference is a key constraint. Applying these metrics to three editions (2023-2025) of the MentalRiskES shared task, we construct the first Green Leaderboard for early risk detection. Our results show that sustainability-aware ranking substantially reshapes system positions, highlighting efficient models that remain undervalued under performance-only evaluation.
%R 10.63317/3cbext6ixjh2
%U https://aclanthology.org/2026.nlp4ecology-1.13/
%U https://doi.org/10.63317/3cbext6ixjh2
%P 144-153
Markdown (Informal)
[Introducing a Green Leaderboard for Sustainable Risk Prediction in Streaming NLP Shared Tasks.](https://aclanthology.org/2026.nlp4ecology-1.13/) (Mármol-Romero et al., NLP4Ecology 2026)
ACL