@inproceedings{hilbert-etal-2026-xplainlp,
title = "{X}plai{NLP} @ {C}limate{C}heck 2026 Task 2: Comparing Hierarchical Approaches for Fine-Grained Climate Disinformation Narrative Classification",
author = "Hilbert, Arthur and
Yang, Jing and
Schmitt, Vera",
editor = "Rehm, Georg and
Dietze, Stefan and
Dessi, Danilo and
Maynard, Diana and
Schimmler, Sonja",
booktitle = "Proceedings of Natural Scientific Language Processing ({NSLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nslp-1.29/",
doi = "10.63317/4ufq9w234tkf",
pages = "289--296",
abstract = "We present our submission to Task{~}2 of the ClimateCheck 2026 shared task on Disinformation Narrative Classification which requires assigning climate-contrarian claims to fine-grained disinformation narratives. Using Qwen3-8B as a fixed backbone, we systematically compare data augmentation, prompt engineering and reinforcement learning techniques. Our experiments show that structured reasoning, particularly a chain-of-thought (CoT) prompting strategy aligned with the taxonomy{'}s hierarchical structure, substantially improves Macro-F1 over both zero-shot baselines and augmentation-based fine-tuning. Our best configuration achieves $\sim$0.625 Macro-F1, ranking first in Task{~}2. Our findings demonstrate that carefully designed hierarchical prompting can rival more complex training interventions in low-resource, highly imbalanced narrative classification settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hilbert-etal-2026-xplainlp">
<titleInfo>
<title>XplaiNLP @ ClimateCheck 2026 Task 2: Comparing Hierarchical Approaches for Fine-Grained Climate Disinformation Narrative Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="family">Hilbert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Schmitt</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 Natural Scientific Language Processing (NSLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Dietze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Dessi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Maynard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our submission to Task 2 of the ClimateCheck 2026 shared task on Disinformation Narrative Classification which requires assigning climate-contrarian claims to fine-grained disinformation narratives. Using Qwen3-8B as a fixed backbone, we systematically compare data augmentation, prompt engineering and reinforcement learning techniques. Our experiments show that structured reasoning, particularly a chain-of-thought (CoT) prompting strategy aligned with the taxonomy’s hierarchical structure, substantially improves Macro-F1 over both zero-shot baselines and augmentation-based fine-tuning. Our best configuration achieves \sim0.625 Macro-F1, ranking first in Task 2. Our findings demonstrate that carefully designed hierarchical prompting can rival more complex training interventions in low-resource, highly imbalanced narrative classification settings.</abstract>
<identifier type="citekey">hilbert-etal-2026-xplainlp</identifier>
<identifier type="doi">10.63317/4ufq9w234tkf</identifier>
<location>
<url>https://aclanthology.org/2026.nslp-1.29/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>289</start>
<end>296</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XplaiNLP @ ClimateCheck 2026 Task 2: Comparing Hierarchical Approaches for Fine-Grained Climate Disinformation Narrative Classification
%A Hilbert, Arthur
%A Yang, Jing
%A Schmitt, Vera
%Y Rehm, Georg
%Y Dietze, Stefan
%Y Dessi, Danilo
%Y Maynard, Diana
%Y Schimmler, Sonja
%S Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F hilbert-etal-2026-xplainlp
%X We present our submission to Task 2 of the ClimateCheck 2026 shared task on Disinformation Narrative Classification which requires assigning climate-contrarian claims to fine-grained disinformation narratives. Using Qwen3-8B as a fixed backbone, we systematically compare data augmentation, prompt engineering and reinforcement learning techniques. Our experiments show that structured reasoning, particularly a chain-of-thought (CoT) prompting strategy aligned with the taxonomy’s hierarchical structure, substantially improves Macro-F1 over both zero-shot baselines and augmentation-based fine-tuning. Our best configuration achieves \sim0.625 Macro-F1, ranking first in Task 2. Our findings demonstrate that carefully designed hierarchical prompting can rival more complex training interventions in low-resource, highly imbalanced narrative classification settings.
%R 10.63317/4ufq9w234tkf
%U https://aclanthology.org/2026.nslp-1.29/
%U https://doi.org/10.63317/4ufq9w234tkf
%P 289-296
Markdown (Informal)
[XplaiNLP @ ClimateCheck 2026 Task 2: Comparing Hierarchical Approaches for Fine-Grained Climate Disinformation Narrative Classification](https://aclanthology.org/2026.nslp-1.29/) (Hilbert et al., NSLP 2026)
ACL