Neyman Orthogonal Activation Steering
This story is from 2026-10-27. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2610.33217v1 Announce Type: new Abstract: Activation steering is a popular approach for shifting LLM output toward a desired behavior, and increasingly for generating realistic synthetic data. The standard recipe estimates a steering direction by contrasting LLM activations on prompts with an…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-27 04:00 · arXiv cs.LG
Neyman Orthogonal Activation Steering