Saved in:
Bibliographic Details
Main Authors: Mondal, Devam, Lipizzi, Carlo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.13925
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910377132949504
author Mondal, Devam
Lipizzi, Carlo
author_facet Mondal, Devam
Lipizzi, Carlo
contents Despite the growing capabilities of large language models, there exists concerns about the biases they develop. In this paper, we propose a novel, automated mechanism for debiasing through specified dataset augmentation in the lens of bias producers and in the context of 'restricted industries' with limited data. We additionally create two new additional metrics, the mb-index and db-index, to quantify bias, considering the idea that bias occurs due to both intrinsic model architecture and dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13925
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reducing Large Language Model Bias with Emphasis on 'Restricted Industries': Automated Dataset Augmentation and Prejudice Quantification
Mondal, Devam
Lipizzi, Carlo
Computation and Language
Artificial Intelligence
Machine Learning
Despite the growing capabilities of large language models, there exists concerns about the biases they develop. In this paper, we propose a novel, automated mechanism for debiasing through specified dataset augmentation in the lens of bias producers and in the context of 'restricted industries' with limited data. We additionally create two new additional metrics, the mb-index and db-index, to quantify bias, considering the idea that bias occurs due to both intrinsic model architecture and dataset.
title Reducing Large Language Model Bias with Emphasis on 'Restricted Industries': Automated Dataset Augmentation and Prejudice Quantification
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2403.13925