uc-davis

Tag

Cards List
#uc-davis

Robust and Efficient Guardrails with Latent Reasoning

arXiv cs.AI · 2026-05-29 Cached

CoLaGuard is a new guardrail model that transfers multi-step safety reasoning into a continuous latent space, achieving 12.9x speedup and 22.4x token reduction compared to explicit reasoning baselines while matching macro-F1 performance on ten safety benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback