SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models

Understand

Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts.

• Following the growing scientific interest in mechanistic interpretability, recent work encoded refusal behavior as a single direction in the model's latent space; e.g., computed as the difference between the centroids of harmful and harmless prompt representations.
• However, emerging evidence suggests that concepts in LLMs often appear to be encoded as a low-dimensional manifold embedded in the high-dimensional latent space.
• Motivated by these findings, we propose a novel method leveraging Self-Organizing Maps (SOMs) to extract multiple refusal directions.