"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals."

Peixuan Han et al. (2025)

> Home

Details and statistics

DOI: —

access: open

type: Conference or Workshop Paper

metadata version: 2026-02-20

- view
  - electronic edition @ aclanthology.org (open access)
- export record
  dblp key:
  - conf/emnlp/HanQCZJZ25
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/emnlp/HanQCZJZ25
Peixuan Han, Cheng Qian, Xiusi Chen, Yuji Zhang, Heng Ji, Denghui Zhang:
SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals. EMNLP (Findings) 2025: 6936-6955

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.