A prompt-only ranker, a direction classifier, and an adaptive gate reproduce most of the oracle's per-instance multi-layer steering benefit with no labels at inference.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models
A prompt-only ranker, a direction classifier, and an adaptive gate reproduce most of the oracle's per-instance multi-layer steering benefit with no labels at inference.