Better Language Model Inversion by Compactly Representing Next-Token Distributions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nazir, Murtaza, Finlayson, Matthew, Morris, John X., Ren, Xiang, Swayamdipta, Swabha
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.17090