---
_id: '59856'
abstract:
- lang: eng
  text: Recent advances on instruction fine-tuning have led to the development of
    various prompting techniques for large language models, such as explicit reasoning
    steps. However, the success of techniques depends on various parameters, such
    as the task, language model, and context provided. Finding an effective prompt
    is, therefore, often a trial-and-error process. Most existing approaches to automatic
    prompting aim to optimize individual techniques instead of compositions of techniques
    and their dependence on the input. To fill this gap, we propose an adaptive prompting
    approach that predicts the optimal prompt composition ad-hoc for a given input.
    We apply our approach to social bias detection, a highly context-dependent task
    that requires semantic understanding. We evaluate it with three large language
    models on three datasets, comparing compositions to individual techniques and
    other baselines. The results underline the importance of finding an effective
    prompt composition. Our approach robustly ensures high detection performance,
    and is best in several settings. Moreover, first experiments on other tasks support
    its generalizability.
author:
- first_name: Maximilian
  full_name: Spliethöver, Maximilian
  id: '84035'
  last_name: Spliethöver
  orcid: 0000-0003-4364-1409
- first_name: Tim
  full_name: Knebler, Tim
  last_name: Knebler
- first_name: Fabian
  full_name: Fumagalli, Fabian
  id: '93420'
  last_name: Fumagalli
- first_name: Maximilian
  full_name: Muschalik, Maximilian
  last_name: Muschalik
- first_name: Barbara
  full_name: Hammer, Barbara
  last_name: Hammer
- first_name: Eyke
  full_name: Hüllermeier, Eyke
  id: '48129'
  last_name: Hüllermeier
- first_name: Henning
  full_name: Wachsmuth, Henning
  id: '3900'
  last_name: Wachsmuth
citation:
  ama: 'Spliethöver M, Knebler T, Fumagalli F, et al. Adaptive Prompting: Ad-hoc Prompt
    Composition for Social Bias Detection. In: Chiruzzo L, Ritter A, Wang L, eds.
    <i>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of
    the Association for Computational Linguistics: Human Language Technologies (Volume
    1: Long Papers)</i>. Association for Computational Linguistics; 2025:2421–2449.'
  apa: 'Spliethöver, M., Knebler, T., Fumagalli, F., Muschalik, M., Hammer, B., Hüllermeier,
    E., &#38; Wachsmuth, H. (2025). Adaptive Prompting: Ad-hoc Prompt Composition
    for Social Bias Detection. In L. Chiruzzo, A. Ritter, &#38; L. Wang (Eds.), <i>Proceedings
    of the 2025 Conference of the Nations of the Americas Chapter of the Association
    for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</i>
    (pp. 2421–2449). Association for Computational Linguistics.'
  bibtex: '@inproceedings{Spliethöver_Knebler_Fumagalli_Muschalik_Hammer_Hüllermeier_Wachsmuth_2025,
    place={Albuquerque, New Mexico}, title={Adaptive Prompting: Ad-hoc Prompt Composition
    for Social Bias Detection}, booktitle={Proceedings of the 2025 Conference of the
    Nations of the Americas Chapter of the Association for Computational Linguistics:
    Human Language Technologies (Volume 1: Long Papers)}, publisher={Association for
    Computational Linguistics}, author={Spliethöver, Maximilian and Knebler, Tim and
    Fumagalli, Fabian and Muschalik, Maximilian and Hammer, Barbara and Hüllermeier,
    Eyke and Wachsmuth, Henning}, editor={Chiruzzo, Luis and Ritter, Alan and Wang,
    Lu}, year={2025}, pages={2421–2449} }'
  chicago: 'Spliethöver, Maximilian, Tim Knebler, Fabian Fumagalli, Maximilian Muschalik,
    Barbara Hammer, Eyke Hüllermeier, and Henning Wachsmuth. “Adaptive Prompting:
    Ad-Hoc Prompt Composition for Social Bias Detection.” In <i>Proceedings of the
    2025 Conference of the Nations of the Americas Chapter of the Association for
    Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</i>,
    edited by Luis Chiruzzo, Alan Ritter, and Lu Wang, 2421–2449. Albuquerque, New
    Mexico: Association for Computational Linguistics, 2025.'
  ieee: 'M. Spliethöver <i>et al.</i>, “Adaptive Prompting: Ad-hoc Prompt Composition
    for Social Bias Detection,” in <i>Proceedings of the 2025 Conference of the Nations
    of the Americas Chapter of the Association for Computational Linguistics: Human
    Language Technologies (Volume 1: Long Papers)</i>, 2025, pp. 2421–2449.'
  mla: 'Spliethöver, Maximilian, et al. “Adaptive Prompting: Ad-Hoc Prompt Composition
    for Social Bias Detection.” <i>Proceedings of the 2025 Conference of the Nations
    of the Americas Chapter of the Association for Computational Linguistics: Human
    Language Technologies (Volume 1: Long Papers)</i>, edited by Luis Chiruzzo et
    al., Association for Computational Linguistics, 2025, pp. 2421–2449.'
  short: 'M. Spliethöver, T. Knebler, F. Fumagalli, M. Muschalik, B. Hammer, E. Hüllermeier,
    H. Wachsmuth, in: L. Chiruzzo, A. Ritter, L. Wang (Eds.), Proceedings of the 2025
    Conference of the Nations of the Americas Chapter of the Association for Computational
    Linguistics: Human Language Technologies (Volume 1: Long Papers), Association
    for Computational Linguistics, Albuquerque, New Mexico, 2025, pp. 2421–2449.'
date_created: 2025-05-10T12:37:45Z
date_updated: 2025-09-12T09:51:30Z
department:
- _id: '660'
editor:
- first_name: Luis
  full_name: Chiruzzo, Luis
  last_name: Chiruzzo
- first_name: Alan
  full_name: Ritter, Alan
  last_name: Ritter
- first_name: Lu
  full_name: Wang, Lu
  last_name: Wang
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://aclanthology.org/2025.naacl-long.122/
oa: '1'
page: 2421–2449
place: Albuquerque, New Mexico
project:
- _id: '118'
  name: 'TRR 318: Project Area INF'
- _id: '126'
  name: TRR 318 - Subproject C3
publication: 'Proceedings of the 2025 Conference of the Nations of the Americas Chapter
  of the Association for Computational Linguistics: Human Language Technologies (Volume
  1: Long Papers)'
publication_identifier:
  isbn:
  - 979-8-89176-189-6
publication_status: published
publisher: Association for Computational Linguistics
related_material:
  link:
  - relation: software
    url: https://github.com/webis-de/naacl25-prompt-compositions
status: public
title: 'Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection'
type: conference
user_id: '84035'
year: '2025'
...