BarrierSteer applies control barrier functions to LLM latent states for constraint-guided steering that reduces unsafe generations while preserving utility.
To ensure statistical significance, results for learning-based methodologies are reported as averages over 5 independent trials with associated standard deviations
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.