SOURCE-LINKED INTELLIGENCE

The Role of Fine-grained Harm Signals in LLM Safety

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Prior work has shown that internal harmfulness representations in large language models vary across risk categories, while sharing a common general harm representation component. This raises a question about the role of the category-specific component beyond general harm representation in LLM safety. To answer this question, we isolate the category-specific component by removing shared general harmfulness representation from each categorical harmfulness representation, yielding a category residual that is orthogonal to general harmfulness at every layer. Using activation steering with category

Read original source ↗ Open in workspace

recordType

paper

region

Global