Model Whisper: Steering Vectors Unlock Large Language Models’ Potential in Test-Time

Xinyue Kang; Diwei Shi; Li Chen

AAAI 2026technical0 citations

Model Whisper: Steering Vectors Unlock Large Language Models’ Potential in Test-Time

Abstract

It is a critical challenge to efficiently unlock the powerful reasoning potential of Large Language Models (LLMs) for specific tasks or new distributions. Existing test-time adaptation methods often require tuning model parameters, which is not only computationally expensive but also risks degrading the model

BibTeX

@inproceedings{aaai2026_modelwhisperstee,
  title = {Model Whisper: Steering Vectors Unlock Large Language Models’ Potential in Test-Time},
  author = {Xinyue Kang and Diwei Shi and Li Chen},
  booktitle = {AAAI 2026},
  year = {2026}
}