PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Avery, Pan, Yangchen, Farahmand, Amir-massoud
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.01925