The Role of Fine-grained Harm Signals in LLM Safety
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 residuals across 11 risk categories in 3 instruction-tuned LLMs, we find that whether category r...
| Authors | Soyeon Park, Seogyeong Jeong, Sunwoo Kim et al. |
|---|---|
| Primary category | cs.CL |
| Published | 16 September 2026 |
| Last updated at source | 18 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.