High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Franzmeyer, Tim, Sravankumar, Archie, Liu, Lijuan, Mao, Yuning, Hou, Rui, Wang, Sinong, Foerster, Jakob N., Zettlemoyer, Luke, Khabsa, Madian
Format:	Preprint
Published:	2025
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/2506.04051