---
_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'
...
---
_id: '57240'
abstract:
- lang: eng
  text: Validating assertions before adding them to a knowledge graph is an essential
    part of its creation and maintenance. Due to the sheer size of knowledge graphs,
    automatic fact-checking approaches have been developed. These approaches rely
    on reference knowledge to decide whether a given assertion is correct. Recent
    hybrid approaches achieve good results by including several knowledge sources.
    However, it is often impractical to provide a sheer quantity of textual knowledge
    or generate embedding models to leverage these hybrid approaches. We present FaVEL,
    an approach that uses algorithm selection and ensemble learning to amalgamate
    several existing fact-checking approaches that rely solely on a reference knowledge
    graph and, hence, use fewer resources than current hybrid approaches. For our
    evaluation, we create updated versions of two existing datasets and a new dataset
    dubbed FaVEL-DS. Our evaluation compares our approach to 15 fact-checking approaches—including
    the state-of-the-art approach HybridFC—on 3 datasets. Our results demonstrate
    that FaVEL outperforms all other approaches significantly by at least 0.04 in
    terms of the area under the ROC curve. Our source code, datasets, and evaluation
    results are open-source and can be found at https://github.com/dice-group/favel.
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: Franck Lionel
  full_name: Tatkeu Pekarou, Franck Lionel
  last_name: Tatkeu Pekarou
- first_name: Ana Alexandra
  full_name: Morim da Silva, Ana Alexandra
  id: '72108'
  last_name: Morim da Silva
- first_name: Axel-Cyrille
  full_name: Ngonga Ngomo, Axel-Cyrille
  id: '65716'
  last_name: Ngonga Ngomo
citation:
  ama: 'Qudus U, Röder M, Tatkeu Pekarou FL, Morim da Silva AA, Ngonga Ngomo A-C.
    FaVEL: Fact Validation Ensemble Learning. In: Rospocher M, Mehwish Alam, eds.
    <i>EKAW 2024</i>. ; 2024.'
  apa: 'Qudus, U., Röder, M., Tatkeu Pekarou, F. L., Morim da Silva, A. A., &#38;
    Ngonga Ngomo, A.-C. (2024). FaVEL: Fact Validation Ensemble Learning. In M. Rospocher
    &#38; Mehwish Alam (Eds.), <i>EKAW 2024</i>.'
  bibtex: '@inproceedings{Qudus_Röder_Tatkeu Pekarou_Morim da Silva_Ngonga Ngomo_2024,
    title={FaVEL: Fact Validation Ensemble Learning}, booktitle={EKAW 2024}, author={Qudus,
    Umair and Röder, Michael and Tatkeu Pekarou, Franck Lionel and Morim da Silva,
    Ana Alexandra and Ngonga Ngomo, Axel-Cyrille}, editor={Rospocher, Marco and Mehwish
    Alam}, year={2024} }'
  chicago: 'Qudus, Umair, Michael Röder, Franck Lionel Tatkeu Pekarou, Ana Alexandra
    Morim da Silva, and Axel-Cyrille Ngonga Ngomo. “FaVEL: Fact Validation Ensemble
    Learning.” In <i>EKAW 2024</i>, edited by Marco Rospocher and Mehwish Alam, 2024.'
  ieee: 'U. Qudus, M. Röder, F. L. Tatkeu Pekarou, A. A. Morim da Silva, and A.-C.
    Ngonga Ngomo, “FaVEL: Fact Validation Ensemble Learning,” in <i>EKAW 2024</i>,
    Amsterdam, Netherlands, 2024.'
  mla: 'Qudus, Umair, et al. “FaVEL: Fact Validation Ensemble Learning.” <i>EKAW 2024</i>,
    edited by Marco Rospocher and Mehwish Alam, 2024.'
  short: 'U. Qudus, M. Röder, F.L. Tatkeu Pekarou, A.A. Morim da Silva, A.-C. Ngonga
    Ngomo, in: M. Rospocher, Mehwish Alam (Eds.), EKAW 2024, 2024.'
conference:
  end_date: 2024-11-28
  location: Amsterdam, Netherlands
  name: 24th International Conference on Knowledge Engineering and Knowledge Management
  start_date: 2024-11-26
corporate_editor:
- Mehwish Alam
date_created: 2024-11-19T14:12:49Z
date_updated: 2025-09-11T09:48:12Z
ddc:
- '600'
department:
- _id: '34'
editor:
- first_name: Marco
  full_name: Rospocher, Marco
  last_name: Rospocher
file:
- access_level: closed
  content_type: application/pdf
  creator: uqudus
  date_created: 2024-11-19T14:14:14Z
  date_updated: 2024-11-19T14:14:14Z
  file_id: '57241'
  file_name: favel.pdf
  file_size: 190661
  relation: main_file
  success: 1
file_date_updated: 2024-11-19T14:14:14Z
has_accepted_license: '1'
keyword:
- fact checking
- ensemble learning
- transfer learning
- knowledge management.
language:
- iso: eng
popular_science: '1'
project:
- _id: '412'
  name: 'NEBULA: Nutzerzentrierte KI-basierte Erkennung von Fake-News und Fehlinformationen'
- _id: '285'
  name: 'SAIL: SAIL - Nachhaltiger Lebenszyklus von intelligenten soziotechnischen
    Systemen'
- _id: '410'
  name: 'KnowGraphs: KnowGraphs: Knowledge Graphs at Scale'
publication: EKAW 2024
quality_controlled: '1'
status: public
title: 'FaVEL: Fact Validation Ensemble Learning'
type: conference
user_id: '83392'
year: '2024'
...