@article{repitsteeringlanguagemodelswithconceptsp, title = {RepIt: Steering Language Models with Concept-Specific Refusal Vectors}, author = {Vincent Siu and Nathan W. Henry and Nicholas Crispino and Yang Liu and Dawn Song and Chenguang Wang}, year = {2025}, eprint = {2509.13281}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.13281}, }