A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia

Lance Calvin Gamboa, Mark Lee


Anthology ID:
2024.paclic-1.29
Volume:
Proceedings of the 38th Pacific Asia Conference on Language, Information and Computation
Month:
December
Year:
2024
Address:
Tokyo, Japan
Editors:
Shirley Dita, Jong-Bok Kim, Ariane Borlongan, Nathaniel Oco
Venue:
PACLIC
SIG:
Publisher:
Tokyo University of Foreign Studies
Note:
Pages:
296–305
Language:
URL:
https://preview.aclanthology.org/landing_page/2024.paclic-1.29/
DOI:
Bibkey:
Cite (ACL):
Lance Calvin Gamboa and Mark Lee. 2024. A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia. In Proceedings of the 38th Pacific Asia Conference on Language, Information and Computation, pages 296–305, Tokyo, Japan. Tokyo University of Foreign Studies.
Cite (Informal):
A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia (Gamboa & Lee, PACLIC 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.paclic-1.29.pdf