Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Talokar, Nivya, Tarun, Ayush K, Mandal, Murari, Andriushchenko, Maksym, Bosselut, Antoine
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.16346