Steering Safely Or Off A Cliff? Rethinking Specificity And Robustness In Inference-time Interventions

Abstract

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 been widely studied, evaluations of whether interventions alter only the intended property remain limited, especially with respect to unintended changes in behaviors related to the