Steering the CensorShip

Orthodoxy means not thinking—not needing to think.
(George Orwell, 1984)

Uncovering Representation Vectors for LLM ‘Thought’ Control

Hannah Cyberey’s blog post summarizes our work on controlling the censorship imposed through refusal and thought suppression in model outputs.

Paper: Hannah Cyberey and David Evans. Steering the CensorShip: Uncovering Representation Vectors for LLM “Thought” Control. 23 April 2025.

Demos:

• 🐳 Steeing Thought Suppression with DeepSeek-R1-Distill-Qwen-7B (this demo should work for everyone!)

• 🦙 Steering Refusal–Compliance with Llama-3.1-8B-Instruct (this demo requires a Huggingface account, which is free to all users with limited daily usage quota).

  Read More…

  Is Taiwan a Country?

  4 March 2025 David Evans, Hannah Cyberey, Yangfeng Ji, censorship, LLM, steering, fairness

  I gave a short talk at an NSF workshop to spark research collaborations between researchers in Taiwan and the United States. My talk was about work Hannah Cyberey is leading on steering the internal representations of LLMs:

  

  Steering around Censorship
  Taiwan-US Cybersecurity Workshop
  Arlington, Virginia
  3 March 2025

  All Posts by Category or Tags.