Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Abdulhai, Marwa, Cheng, Ryan, Shrivastava, Aryansh, Jaques, Natasha, Gal, Yarin, Levine, Sergey
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/2510.14318