Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Chenhan, Huang, Fei, Peng, Ru, Lu, Keming, Yu, Bowen, Zhou, Chang, Zhou, Jingren
Format:	Preprint
Published:	2024
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/2408.10764