Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shirafuji, Daiki, Takenaka, Makoto, Taguchi, Shinya
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.11679