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

Zhenhong Zhou et al. (2024)

> Home

Details and statistics

DOI: —

access: open

type: Conference or Workshop Paper

metadata version: 2025-02-19

- view
  - electronic edition @ aclanthology.org (open access)
- export record
  dblp key:
  - conf/emnlp/ZhouYZXHL24
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/emnlp/ZhouYZXHL24
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Yongbin Li:
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States. EMNLP (Findings) 2024: 2461-2488

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.