@inproceedings{bonenkamp-etal-2026-proportionate,
title = "Proportionate Responses: The Case for Small Language Models as Sustainable Expert Climate Policy Annotators",
author = "Bonenkamp, Jetske and
Biesbroek, Robbert and
Athanasiadis, Ioannis N.",
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-1.21/",
pages = "315--340",
ISBN = "979-8-89176-465-1",
abstract = "Tracking progress on climate change adaptation requires systematic and robust annotation of adaptation policies, but manual annotation has become infeasible due to the rapidly growing volume of unstructured documents. Pre-trained language models (LMs) have emerged as promising tools for automating and scaling annotation. However, relatively little is known about their accuracy and quality on complex, free-text annotation tasks. Meanwhile, large LMs (LLMs) are increasingly deployed for large scale text analyses despite their considerable environmental footprint and limited exploration of more sustainable alternatives. By benchmarking model accuracy against human inter-annotator agreement, reviewing perceived annotation quality, and estimating energy and water consumption, we show that fine-tuning small LMs (SLMs) provides a substantially more sustainable alternative to LLMs with only marginal reductions in accuracy and improved perceived annotation quality. Furthermore, we demonstrate the importance of evaluating complex annotation tasks beyond accuracy against human gold standard annotation as ambiguity and human error can obscure meaningful differences in model performance. By reducing the costs of high-quality policy annotation, our approach enables the scalable knowledge extraction needed for tracking progress on adaptation, living evidence syntheses, and evidence-informed policy evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bonenkamp-etal-2026-proportionate">
<titleInfo>
<title>Proportionate Responses: The Case for Small Language Models as Sustainable Expert Climate Policy Annotators</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jetske</namePart>
<namePart type="family">Bonenkamp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robbert</namePart>
<namePart type="family">Biesbroek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Athanasiadis</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>Tracking progress on climate change adaptation requires systematic and robust annotation of adaptation policies, but manual annotation has become infeasible due to the rapidly growing volume of unstructured documents. Pre-trained language models (LMs) have emerged as promising tools for automating and scaling annotation. However, relatively little is known about their accuracy and quality on complex, free-text annotation tasks. Meanwhile, large LMs (LLMs) are increasingly deployed for large scale text analyses despite their considerable environmental footprint and limited exploration of more sustainable alternatives. By benchmarking model accuracy against human inter-annotator agreement, reviewing perceived annotation quality, and estimating energy and water consumption, we show that fine-tuning small LMs (SLMs) provides a substantially more sustainable alternative to LLMs with only marginal reductions in accuracy and improved perceived annotation quality. Furthermore, we demonstrate the importance of evaluating complex annotation tasks beyond accuracy against human gold standard annotation as ambiguity and human error can obscure meaningful differences in model performance. By reducing the costs of high-quality policy annotation, our approach enables the scalable knowledge extraction needed for tracking progress on adaptation, living evidence syntheses, and evidence-informed policy evaluation.</abstract>
<identifier type="citekey">bonenkamp-etal-2026-proportionate</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.21/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>315</start>
<end>340</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Proportionate Responses: The Case for Small Language Models as Sustainable Expert Climate Policy Annotators
%A Bonenkamp, Jetske
%A Biesbroek, Robbert
%A Athanasiadis, Ioannis N.
%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 bonenkamp-etal-2026-proportionate
%X Tracking progress on climate change adaptation requires systematic and robust annotation of adaptation policies, but manual annotation has become infeasible due to the rapidly growing volume of unstructured documents. Pre-trained language models (LMs) have emerged as promising tools for automating and scaling annotation. However, relatively little is known about their accuracy and quality on complex, free-text annotation tasks. Meanwhile, large LMs (LLMs) are increasingly deployed for large scale text analyses despite their considerable environmental footprint and limited exploration of more sustainable alternatives. By benchmarking model accuracy against human inter-annotator agreement, reviewing perceived annotation quality, and estimating energy and water consumption, we show that fine-tuning small LMs (SLMs) provides a substantially more sustainable alternative to LLMs with only marginal reductions in accuracy and improved perceived annotation quality. Furthermore, we demonstrate the importance of evaluating complex annotation tasks beyond accuracy against human gold standard annotation as ambiguity and human error can obscure meaningful differences in model performance. By reducing the costs of high-quality policy annotation, our approach enables the scalable knowledge extraction needed for tracking progress on adaptation, living evidence syntheses, and evidence-informed policy evaluation.
%U https://aclanthology.org/2026.climatenlp-1.21/
%P 315-340
Markdown (Informal)
[Proportionate Responses: The Case for Small Language Models as Sustainable Expert Climate Policy Annotators](https://aclanthology.org/2026.climatenlp-1.21/) (Bonenkamp et al., ClimateNLP 2026)
ACL