Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning

Jingyu Hu, Weiru Liu, Mengnan Du


Abstract
Recent studies highlight the effectiveness of using in-context learning (ICL) to steer large language models (LLMs) in processing tabular data, a challenging task given the structured nature of such data. Despite advancements in performance, the fairness implications of these methods are less understood. This study investigates how varying demonstrations within ICL prompts influence the fairness outcomes of LLMs. Our findings reveal that deliberately including minority group samples in prompts significantly boosts fairness without sacrificing predictive accuracy. Further experiments demonstrate that the proportion of minority to majority samples in demonstrations affects the trade-off between fairness and prediction accuracy. Based on these insights, we introduce a mitigation technique that employs clustering and evolutionary strategies to curate a diverse and representative sample set from the training data. This approach aims to enhance both predictive performance and fairness in ICL applications. Experimental results validate that our proposed method dramatically improves fairness across various metrics, showing its efficacy in real-world scenarios.
Anthology ID:
2024.emnlp-main.425
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7460–7475
Language:
URL:
https://aclanthology.org/2024.emnlp-main.425
DOI:
Bibkey:
Cite (ACL):
Jingyu Hu, Weiru Liu, and Mengnan Du. 2024. Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7460–7475, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning (Hu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.425.pdf