LPG compresses policy deliberation into 10 latent tokens to reach 84.5% safety accuracy and 11x speedup over explicit reasoning baselines on guardrail benchmarks.
Prism: Robust vlm alignment with principled reasoning for integrated safety in multimodality.arXiv preprint arXiv:2508.18649, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
LPG compresses policy deliberation into 10 latent tokens to reach 84.5% safety accuracy and 11x speedup over explicit reasoning baselines on guardrail benchmarks.