RFM-AGOP identifies multi-dimensional refusal subspaces in seconds

Researchers have adapted the Recursive Feature Machine (RFM) algorithm with probe-informed initialization to efficiently identify multi-dimensional refusal subspaces in Large Language Models. This approach allows for subspace extraction in seconds on both reasoning models like Qwen 3 and non-reasoning models like Qwen 2.5, addressing the computational prohibitions of existing methods.

• The method leverages RFM to compute subspaces significantly faster than previous techniques.
• It achieves better performance on ablation tasks compared to alternative subspace extraction methods.
• The technique is applicable to both reasoning and non-reasoning model architectures.

RFM serves as a cheap and scalable complement to existing subspace-extraction methods, facilitating more accessible safety monitoring and interpretability analysis in LLMs.