How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Hongzhe, Li, Weikai, Cai, Min, Saraipour, Karim, Zhang, Zimin, Lakkaraju, Himabindu, Sun, Yizhou, Zhang, Shichang
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.02904