Nature Communications

Revealing the intrinsic ethical vulnerability of aligned large language models

• Jiawei Lian
• Jianhong Pan
• Lefan Wang
• Yi Wang
• Xiaofei Wang
• Yingjie Lu
• Shaohui Mei
• Lap-Pui Chau

2026-03-21

Full text

DOI https://doi.org/10.1038/s41467-026-70917-y