Skip to content

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States.

Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Yongbin Li

VenueA*EMNLP
Year2024
ProceedingsEMNLP (Findings)

Browse the full EMNLP paper archive.