---
_id: '56983'
abstract:
- lang: eng
  text: Detecting the veracity of a statement automatically is a challenge the world
    is grappling with due to the vast amount of data spread across the web. Verifying
    a given claim typically entails validating it within the framework of supporting
    evidence like a retrieved piece of text. Classifying the stance of the text with
    respect to the claim is called stance classification. Despite advancements in
    automated fact-checking, most systems still rely on a substantial quantity of
    labeled training data, which can be costly. In this work, we avoid the costly
    training or fine-tuning of models by reusing pre-trained large language models
    together with few-shot in-context learning. Since we do not train any model, our
    approach ExPrompt is lightweight, demands fewer resources than other stance classification
    methods and can serve as a modern baseline for future developments. At the same
    time, our evaluation shows that our approach is able to outperform former state-of-the-art
    stance classification approaches regarding accuracy by at least 2 percent. Our
    scripts and data used in this paper are available at https://github.com/dice-group/ExPrompt.
author:
- first_name: Umair
  full_name: Qudus, Umair
  id: '83392'
  last_name: Qudus
  orcid: 0000-0001-6714-8729
- first_name: Michael
  full_name: Röder, Michael
  id: '67199'
  last_name: Röder
  orcid: https://orcid.org/0000-0002-8609-8277
- first_name: Daniel
  full_name: Vollmers, Daniel
  last_name: Vollmers
- first_name: Axel-Cyrille
  full_name: Ngonga Ngomo, Axel-Cyrille
  id: '65716'
  last_name: Ngonga Ngomo
citation:
  ama: 'Qudus U, Röder M, Vollmers D, Ngonga Ngomo A-C. ExPrompt: Augmenting Prompts
    Using Examples as Modern Baseline for Stance Classification. In: <i>Proceedings
    of the 33rd ACM International Conference on Information and Knowledge Management</i>.
    Vol 9. ACM; 2024:3994-3999. doi:<a href="https://doi.org/10.1145/3627673.3679923">10.1145/3627673.3679923</a>'
  apa: 'Qudus, U., Röder, M., Vollmers, D., &#38; Ngonga Ngomo, A.-C. (2024). ExPrompt:
    Augmenting Prompts Using Examples as Modern Baseline for Stance Classification.
    <i>Proceedings of the 33rd ACM International Conference on Information and Knowledge
    Management</i>, <i>9</i>, 3994–3999. <a href="https://doi.org/10.1145/3627673.3679923">https://doi.org/10.1145/3627673.3679923</a>'
  bibtex: '@inproceedings{Qudus_Röder_Vollmers_Ngonga Ngomo_2024, title={ExPrompt:
    Augmenting Prompts Using Examples as Modern Baseline for Stance Classification},
    volume={9}, DOI={<a href="https://doi.org/10.1145/3627673.3679923">10.1145/3627673.3679923</a>},
    booktitle={Proceedings of the 33rd ACM International Conference on Information
    and Knowledge Management}, publisher={ACM}, author={Qudus, Umair and Röder, Michael
    and Vollmers, Daniel and Ngonga Ngomo, Axel-Cyrille}, year={2024}, pages={3994–3999}
    }'
  chicago: 'Qudus, Umair, Michael Röder, Daniel Vollmers, and Axel-Cyrille Ngonga
    Ngomo. “ExPrompt: Augmenting Prompts Using Examples as Modern Baseline for Stance
    Classification.” In <i>Proceedings of the 33rd ACM International Conference on
    Information and Knowledge Management</i>, 9:3994–99. ACM, 2024. <a href="https://doi.org/10.1145/3627673.3679923">https://doi.org/10.1145/3627673.3679923</a>.'
  ieee: 'U. Qudus, M. Röder, D. Vollmers, and A.-C. Ngonga Ngomo, “ExPrompt: Augmenting
    Prompts Using Examples as Modern Baseline for Stance Classification,” in <i>Proceedings
    of the 33rd ACM International Conference on Information and Knowledge Management</i>,
    Boise, ID, USA, 2024, vol. 9, pp. 3994–3999, doi: <a href="https://doi.org/10.1145/3627673.3679923">10.1145/3627673.3679923</a>.'
  mla: 'Qudus, Umair, et al. “ExPrompt: Augmenting Prompts Using Examples as Modern
    Baseline for Stance Classification.” <i>Proceedings of the 33rd ACM International
    Conference on Information and Knowledge Management</i>, vol. 9, ACM, 2024, pp.
    3994–99, doi:<a href="https://doi.org/10.1145/3627673.3679923">10.1145/3627673.3679923</a>.'
  short: 'U. Qudus, M. Röder, D. Vollmers, A.-C. Ngonga Ngomo, in: Proceedings of
    the 33rd ACM International Conference on Information and Knowledge Management,
    ACM, 2024, pp. 3994–3999.'
conference:
  end_date: 2024-10-25
  location: Boise, ID, USA
  name: 'CIKM ''24: Proceedings of the 33rd ACM International Conference on Information
    and Knowledge Management'
  start_date: 2024-10-21
date_created: 2024-11-11T13:15:25Z
date_updated: 2025-09-11T09:49:07Z
ddc:
- '006'
doi: 10.1145/3627673.3679923
file:
- access_level: closed
  content_type: application/pdf
  creator: uqudus
  date_created: 2024-11-11T13:24:19Z
  date_updated: 2024-11-11T13:24:19Z
  file_id: '56984'
  file_name: public.pdf
  file_size: 531579
  relation: main_file
  success: 1
file_date_updated: 2024-11-11T13:24:19Z
has_accepted_license: '1'
intvolume: '         9'
keyword:
- Stance Classification
- Few-shot in-context learning
- Pre-trained large language models
language:
- iso: eng
main_file_link:
- url: https://dl.acm.org/doi/10.1145/3627673.3679923
page: 3994 - 3999
popular_science: '1'
project:
- _id: '412'
  name: 'NEBULA: Nutzerzentrierte KI-basierte Erkennung von Fake-News und Fehlinformationen'
publication: Proceedings of the 33rd ACM International Conference on Information and
  Knowledge Management
publication_identifier:
  isbn:
  - 79-8-4007-0436-9/24/10
publication_status: published
publisher: ACM
quality_controlled: '1'
status: public
title: 'ExPrompt: Augmenting Prompts Using Examples as Modern Baseline for Stance
  Classification'
type: conference
user_id: '83392'
volume: 9
year: '2024'
...