RepIt: Steering Language Models with Concept-Specific Refusal Vectors
Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simple and data-efficient framework for isolating concept-specific representations in LM activations. While existing steering methods already achieve high attack success rates through broad interventions, RepIt enables a more concerning capability: selective suppression of refusal on targeted concepts while preserving refusal elsewhere. Across five frontier LMs, RepIt produces evaluation-evading model organisms with semantic backdoors, answering questions related to weapons of mass destruction while still scoring as safe on standard benchmarks. We find the edit of the steering vector localizes to just 100-200 residual dimensions, and robust concept vectors can be extracted from as few as a dozen examples on a single RTX A6000, highlighting how targeted, hard-to-detect modifications can exploit evaluation blind spots with minimal resources. Through demonstrating precise concept disentanglement, this work exposes vulnerabilities in current safety evaluation practices and demonstrates a need for more comprehensive, representation aware assessments.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Expert-Aware Refusal Steering
Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed requests. Recent work has shown that a steering vector can be applied…
There Is More to Refusal in Large Language Models than a Single Direction
Prior work argues that refusal in large language models is mediated by a single direction, enabling steering and abliteration. We show that this account is incomplete: across diverse refusal and non-compliance categories…
What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steeri…
Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions
Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has …
From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions
Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In t…