Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
Source
arxiv.org
Author
Philipp E. Glass, Allan Tucker, Yongmin Li, Alina Miron
Date
Why it matters
Steering embedded into weights does not survive routine post-deployment fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition → behaviourally, even though the edit remains in the weights — so pre-release weight-level alignmentThe work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.Full definition → cannot be assumed to hold downstream.
Terms in this piece · Glossary
embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
alignment — The work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
videoSteering LLM Behavior Without Fine-TuningHugging Face
articleFrom Detection to Refusal: Safer LLMs via Circuit-Guided Weight ScalingKuan-Lin Chu, Chung-En Sun, Tsui-Wei Weng
articleCan a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for AbstentionAli Asaria, Tony Salomone, Deep Gandhi