How to Tame a Multi-Headed Hydra? Adaptive Multi-Category Safety Steering for Large Language Models
As large language models (LLMs) become increasingly widespread, preventing unsafe responses to harmful prompts is essential for their safe deployment. Activation steering offers an approach to improving LLM safety by modifying internal activations during inference without updating model parameters. However, a single prompt can involve multiple harm categories, and steering toward safety in one category may leave harmful content from another unaddressed. Despite advances in adaptive steering, existing methods do not explicitly coordinate steering direction and strength when multiple harm categories co-occur within a single prompt. To address this problem, we propose CAM-Steer, a Category-A...
| Authors | Chenxi Wang, Ruiyang Huang, Li Huang et al. |
|---|---|
| Primary category | cs.CR |
| Published | 28 September 2026 |
| Last updated at source | 29 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 Information may be incomplete or out of date.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.