Biases in Large Language Models: Origins, Inventory, and Discussion
Journal of Data and Information Quality · 30.06.2023 · 15 (2) · 1-21
DOI: 10.1145/3597307 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Data and Information Quality, online erschienen am 22.06.2023. Verfasst von Roberto Navigli und 2 weiteren Autor:innen. Die Arbeit wurde bisher 368-mal zitiert (Crossref) und nennt 132 Literaturangaben.
Abstract (Originalsprache)
In this article, we introduce and discuss the pervasive issue of bias in the large language models that are currently at the core of mainstream approaches to Natural Language Processing (NLP). We first introduce data selection bias, that is, the bias caused by the choice of texts that make up a training corpus. Then, we survey the different types of social bias evidenced in the text generated by language models trained on such corpora, ranging from gender to age, from sexual orientation to ethnicity, and from religion to culture. We conclude with directions focused on measuring, reducing, and tackling the aforementioned types of bias.
Zitieren
APA
Navigli, R., Conia, S., & Ross, B. (2023). Biases in Large Language Models: Origins, Inventory, and Discussion. Journal of Data and Information Quality, 15(2), 1-21. https://doi.org/10.1145/3597307
Vancouver
Navigli R, Conia S, Ross B. Biases in Large Language Models: Origins, Inventory, and Discussion. Journal of Data and Information Quality. 2023;15(2):1-21. doi:10.1145/3597307
BibTeX
@article{Navigli2023,
author = {Navigli, Roberto and Conia, Simone and Ross, Björn},
title = {Biases in Large Language Models: Origins, Inventory, and Discussion},
journal = {Journal of Data and Information Quality},
year = {2023},
volume = {15},
number = {2},
pages = {1--21},
doi = {10.1145/3597307}
}
EUVIMED