Priors in Time: Missing Inductive Biases for Language Model Interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lubana, Ekdeep Singh, Rager, Can, Hindupur, Sai Sumedh R., Costa, Valerie, Tuckute, Greta, Patel, Oam, Murthy, Sonia Krishna, Fel, Thomas, Wurgaft, Daniel, Bigelow, Eric J., Lin, Johnny, Ba, Demba, Wattenberg, Martin, Viegas, Fernanda, Weber, Melanie, Mueller, Aaron
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2511.01836