BarrierSteer applies control barrier functions to LLM latent states for constraint-guided steering that reduces unsafe generations while preserving utility.
Closed-form of BARRIERSTEER In order to efficiently enforce the proposed BARRIERSTEER, we first merge many constraints into no-greater than two constraints, as (7) shown in Sec
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BarrierSteer: LLM Safety via Learning Barrier Steering
BarrierSteer applies control barrier functions to LLM latent states for constraint-guided steering that reduces unsafe generations while preserving utility.