Genesis Steering: Better Activation Steering Through Training Data
arXiv:2610.19114v1 Announce Type: new Abstract: Activation steering controls large language models at inference time, but its effectiveness depends on the choice of reference data. We introduce genesis steering, which derives a genesis vector from contrastive examples in the model's own fine-tuning…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-15 04:00 · arXiv cs.LG
Genesis Steering: Better Activation Steering Through Training Data