Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning
Document Type
Conference Proceeding
Publication Date
1-1-2024
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.
Identifier
85217826087 (Scopus)
ISBN
[9798891761643]
Publication Title
EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
External Full Text Location
https://doi.org/10.18653/v1/2024.emnlp-main.425
First Page
7460
Last Page
7475
Recommended Citation
Hu, Jingyu; Liu, Weiru; and Du, Mengnan, "Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning" (2024). Faculty Publications. 719.
https://digitalcommons.njit.edu/fac_pubs/719