TY - GEN

T1 - Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection

AU - Spliethöver, Maximilian

AU - Knebler, Tim

AU - Fumagalli, Fabian

AU - Muschalik, Maximilian

AU - Hammer, Barbara

AU - Hüllermeier, Eyke

AU - Wachsmuth, Henning

PY - 2025/4/29

Y1 - 2025/4/29

N2 - 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.

AB - 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.

M3 - Conference contribution

VL - 1

BT - Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

CY - Albuquerque, New Mexico

ER -