[2509.13281] RepIt: Steering Language Models with Concept-Specific Refusal Vectors

[2509.13281] RepIt: Steering Language Models with Concept-Specific Refusal Vectors

Summary

Abstract page for arXiv paper 2509.13281: RepIt: Steering Language Models with Concept-Specific Refusal Vectors

Description

Abstract page for arXiv paper 2509.13281: RepIt: Steering Language Models with Concept-Specific Refusal Vectors

Original reporting

AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.

Open original source

Related coverage