PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under a Subspace Calibration

Reliable behavior control is central to deploying Large Language Models (LLMs) on the web. Activation steering offers a tuning-free route to align attributes (e.g., truthfulness) that ensure trustworthy generation. Prevailing approaches rely on coarse heuristics and lack a principled account of where to steer and how strongly to intervene. To this end, we propose Position-wise Injection with eXact Estimated Levels (PIXEL), a position-wise activation steering framework that, in contrast to prior work, learns a property-aligned subspace from dual views (tail-averaged and end-token) and selects intervention strength via a constrained geometric objective with a closed-form solution, thereby adapting to token-level sensitivity without global hyperparameter tuning. PIXEL further performs sample-level orthogonal residual calibration to refine the global attribute direction and employs a lightweight position-scanning routine to identify receptive injection sites. We additionally provide representation-level guarantees for the minimal-intervention rule, supporting reliable alignment. Across diverse models and evaluation paradigms, PIXEL consistently improves attribute alignment while preserving model general capabilities, offering a practical and principled method for LLMs' controllable generation. Our code is available at https://anonymous.4open.science/r/PIXEL-Adaptive-Steering-95DC

Citation

M. Yu, H. Li, P. Singh, X. Li, D. Wang, L. Hu, "PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under a Subspace Calibration," 2026, pp. 1574-1585.

Conference

ACM Web Conference 2026

Keywords

46 Information and Computing Sciences, 4607 Graphics, Augmented Reality and Games

Source

ACM Web Conference 2026

Publisher

Association for Computing Machinery

DOI

10.1145/3774904.3792273

Additional links

https://dl.acm.org/doi/10.1145/3774904.3792273