From Weights to Activations: Is Steering the Next Frontier of Adaptation?

MCML Authors

Michael Hedderich

Dr.

JRG Leader Human-Centered NLP

AI and Computational Linguistics

Abstract

Post-training adaptation of large language models is commonly achieved through parameter updates or input based methods such as fine-tuning, parameter-efficient adaptation, and prompting. In parallel, a growing body of work modifies internal activations at inference time to influence model behavior, an approach known as *steering*. Despite increasing use, steering is rarely analyzed within the same conceptual framework as established adaptation methods.In this work, we argue that steering should be regarded as a form of model adaptation. We introduce a set of functional criteria for adaptation methods and use them to compare steering approaches with classical alternatives. This analysis positions steering as a distinct adaptation paradigm based on targeted interventions in activation space, enabling local and reversible behavioral change without parameter updates. The resulting framing clarifies how steering relates to existing methods, motivating a unified taxonomy for model adaptation.

inproceedings OGB+26

---

ACL 2026

64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026.

---

Authors

S. Ostermann • D. Gurgurov • T. Baeumel • M. A. Hedderich • S. Lapuschkin • W. Samek • V. Schmitt

---

Links

DOI

---

In Collaboration

---

Research Area

 B2 | Natural Language Processing