@inproceedings{schulten-etal-2026-climatextract,
title = "Climatextract: A Systematic Prompt Evaluation For Climate Information Extraction",
author = "Schulten, Anna Steinberg and
Schierholz, Malte and
Reichenbach, Lisa and
Kreuter, Frauke and
Fraser, Alexander",
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-1.3/",
pages = "29--40",
ISBN = "979-8-89176-465-1",
abstract = "Automated extraction of corporate greenhouse gas (GHG) emissions from sustainability reports is critical for climate crisis governance, yet the choice of prompt design, context provision, and model in LLM-based pipelines is largely guided by informal best-practice recommendations rather than systematic evaluation. With **Climatextract**, we assess these choices in a RAG pipeline, comparing closed-source against open-weight models, a structured ``best-practice'' prompt against a simple question-style prompt, and text-only against text-plus-table contexts. We find that performance is non-monotonic across model generations, a structured prompt with roles, definitions, extraction rules, and JSON formatting is significantly outperformed by a question-style prompt, and tabular context helps only in a specific model-prompt combination. A cost-benefit analysis shows that performance gains are often disproportionate to cost increases."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schulten-etal-2026-climatextract">
<titleInfo>
<title>Climatextract: A Systematic Prompt Evaluation For Climate Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="given">Steinberg</namePart>
<namePart type="family">Schulten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malte</namePart>
<namePart type="family">Schierholz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Reichenbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frauke</namePart>
<namePart type="family">Kreuter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</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>Automated extraction of corporate greenhouse gas (GHG) emissions from sustainability reports is critical for climate crisis governance, yet the choice of prompt design, context provision, and model in LLM-based pipelines is largely guided by informal best-practice recommendations rather than systematic evaluation. With **Climatextract**, we assess these choices in a RAG pipeline, comparing closed-source against open-weight models, a structured “best-practice” prompt against a simple question-style prompt, and text-only against text-plus-table contexts. We find that performance is non-monotonic across model generations, a structured prompt with roles, definitions, extraction rules, and JSON formatting is significantly outperformed by a question-style prompt, and tabular context helps only in a specific model-prompt combination. A cost-benefit analysis shows that performance gains are often disproportionate to cost increases.</abstract>
<identifier type="citekey">schulten-etal-2026-climatextract</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.3/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>29</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Climatextract: A Systematic Prompt Evaluation For Climate Information Extraction
%A Schulten, Anna Steinberg
%A Schierholz, Malte
%A Reichenbach, Lisa
%A Kreuter, Frauke
%A Fraser, Alexander
%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 schulten-etal-2026-climatextract
%X Automated extraction of corporate greenhouse gas (GHG) emissions from sustainability reports is critical for climate crisis governance, yet the choice of prompt design, context provision, and model in LLM-based pipelines is largely guided by informal best-practice recommendations rather than systematic evaluation. With **Climatextract**, we assess these choices in a RAG pipeline, comparing closed-source against open-weight models, a structured “best-practice” prompt against a simple question-style prompt, and text-only against text-plus-table contexts. We find that performance is non-monotonic across model generations, a structured prompt with roles, definitions, extraction rules, and JSON formatting is significantly outperformed by a question-style prompt, and tabular context helps only in a specific model-prompt combination. A cost-benefit analysis shows that performance gains are often disproportionate to cost increases.
%U https://aclanthology.org/2026.climatenlp-1.3/
%P 29-40
Markdown (Informal)
[Climatextract: A Systematic Prompt Evaluation For Climate Information Extraction](https://aclanthology.org/2026.climatenlp-1.3/) (Schulten et al., ClimateNLP 2026)
ACL