To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

摘要

We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventions. Unlike existing methods that rely on fixed, manually tuned steering strengths, often resulting in under or oversteering, MERA addresses these limitations by (i) optimising the intervention direction, and (ii) calibrating when and how much to steer, thereby provably improving performance or abstaining when no confident correction is possible. Experiments across diverse datasets and LM families demonstrate safe, effective, non-degrading error correction and that MERA outperforms existing baselines. Moreover, MERA can be applied on top of existing steering techniques to further enhance their performance, establishing it as a general-purpose and efficient approach to mechanistic activation steering.