On Demonstration Selection for Improving Language Model Fairness
Abstract: Recently, there has been a surge in deploying Large Language Models (LLMs) for decision-making tasks, such as income prediction and crime risk assessments. Due to bias in the pre-training data, LLMs generally present unfairness and discrimination against underprivileged groups. However, traditional fairness enhancement methods are generally impractical for LLMs due to the computational cost of fine-tuning and the black-box nature of powerful LLMs. To deal with this, In-Context Learning (ICL) offers a promising strategy for enhancing LLM fairness through input-output pairs, without the need for extensive retraining. Nevertheless, the efficacy of ICL is hindered by the inherent bias in both data and the LLM itself, leading to the potential exaggeration of existing societal disparities. In this study, we investigate the unfairness problem in LLMs and propose a novel demonstration selection strategy to address data and model biases when applying ICL. Extensive experiments on various tasks and datasets validate the superiority of our strategy.
Paper Type: Long
Research Area: Ethics, Bias, and Fairness
Research Area Keywords: Fairness, In-context Learning, Large Language Models
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Reproduction study, Publicly available software and/or pre-trained models, Data resources, Data analysis
Languages Studied: English
Section 2 Permission To Publish Peer Reviewers Content Agreement: Authors grant permission for ACL to publish peer reviewers' content
Submission Number: 505
Loading