Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
Authors: Xianjun Yang, Xiao Wang, Qi Zhang, Linda Petzold, William Yang Wang, Xun Zhao, Dahua Lin | Published: 2023-10-04
安全性アライメント
Low-Resource Languages Jailbreak GPT-4
Authors: Zheng-Xin Yong, Cristina Menghini, Stephen H. Bach | Published: 2023-10-03 | Updated: 2024-01-27
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
Authors: Bochuan Cao, Yuanpu Cao, Lu Lin, Jinghui Chen | Published: 2023-09-18 | Updated: 2024-06-12
Censoring chemical data to mitigate dual use risk
Authors: Quintina L. Campbell, Jonathan Herington, Andrew D. White | Published: 2023-04-20
Alignment with human representations supports robust few-shot learning
Authors: Ilia Sucholutsky, Thomas L. Griffiths | Published: 2023-01-27 | Updated: 2023-10-29