Evaluating the Efficacy of Prompting Techniques for Debiasing Language Model Outputs (Student Abstract)
Abstract
Achieving fairness in Large Language Models (LLMs) continues to pose a persistent challenge, as these models are prone to inheriting biases from their training data, which can subsequently impact their performance in various applications. There is a need to systematically explore whether structured prompting techniques can offer opportunities for debiased text generation by LLMs. In this work, we designed an evaluative framework to test the efficacy of different prompting techniques for debiasing text along different dimensions. We aim to devise a general structured prompting approach to achieve fairness that generalizes well to different texts and LLMs.
Cite
Text
Furniturewala et al. "Evaluating the Efficacy of Prompting Techniques for Debiasing Language Model Outputs (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30443Markdown
[Furniturewala et al. "Evaluating the Efficacy of Prompting Techniques for Debiasing Language Model Outputs (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/furniturewala2024aaai-evaluating/) doi:10.1609/AAAI.V38I21.30443BibTeX
@inproceedings{furniturewala2024aaai-evaluating,
title = {{Evaluating the Efficacy of Prompting Techniques for Debiasing Language Model Outputs (Student Abstract)}},
author = {Furniturewala, Shaz and Jandial, Surgan and Java, Abhinav and Shahid, Simra and Banerjee, Pragyan and Krishnamurthy, Balaji and Bhatia, Sumit and Jaidka, Kokil},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {23492-23493},
doi = {10.1609/AAAI.V38I21.30443},
url = {https://mlanthology.org/aaai/2024/furniturewala2024aaai-evaluating/}
}