Robust and Efficient Guardrails with Latent Reasoning
Quick Answer
COLAGUARD introduces a novel guardrail model that enhances safety for large language models (LLMs) by utilizing latent reasoning, achieving an 8.24-point improvement in macro-F1 over Llama Guard 3 while delivering a 12.9X speedup and 22.4X reduction in token usage.
Quick Take
This model effectively balances safety robustness and inference efficiency, making it practical for high-throughput deployment.
Key Points
- COLAGUARD improves macro-F1 by 8.24 points over Llama Guard 3.
- Achieves a 12.9X speedup and 22.4X reduction in token usage.
- Utilizes latent reasoning for enhanced safety in .
- Proposed model matches performance of GuardReasoner in macro-F1.
- Addresses challenges of existing reasoning-based guardrails.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2605. 29068v1 Announce Type: new Abstract: Maintaining the safety of (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning. Reasoning-based guardrails significantly outperform classification-only baselines, but they incur substantial query latency and token overhead that make them impractical for highthroughput deployment.
To address this challenge, we propose COLAGUARD, a guardrail model that transfers multi-step safety reasoning into a continuous latent space through a stage-wise training curriculum, enabling direct hidden-state propagation at inference. Evaluated on ten prompt- and response-moderation settings spanning eight safety benchmarks, COLAGUARD improves macro-F1 by 8. 24 points over Llama Guard 3 and matches our explicit reasoning baseline, GuardReasoner, in macroF1 while delivering a 12. 9X speedup and 22.
4X reduction in token usage. Our results suggest that latent reasoning offers a practical alternative to explicit rationale generation for deployable guardrails, jointly improving safety robustness and inference efficiency rather than treating them as competing objectives.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.