PSR models that estimate token-specific steering coefficients from activations outperform standard activation steering and compare favorably to prompting on steering benchmarks.
Fine-tuning aligned language models compromises safety, even when users do not intend to!
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Steer Like the LLM: Activation Steering that Mimics Prompting
PSR models that estimate token-specific steering coefficients from activations outperform standard activation steering and compare favorably to prompting on steering benchmarks.