Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.07473 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- As models grow more capable, humans cannot reliably verify what they say. Scalable steering requires methods that are internal, self-supervised, and transfer out-of-distribution; existing methods satisfy some but not all three. We introduce AntiPaSTO, which separates representations along an antiparallel axis (+1/-1 produce opposite shifts), with coherence constraints preventing collapse. Training uses only two contrasting words inserted into template sentences, with no preference labels. When we use 800 such synthetic pairs on Gemma-3-1B, AntiPaSTO beats prompting baselines by 6.9x Steering F1 on DailyDilemmas and wins on 5 of 6 tested value axes. We also find preliminary evidence that it maintains bidirectional control where prompting triggers refusal.