# LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards

arXiv: https://arxiv.org/abs/2608.03838 · HTML: https://mlsanity.com/paper/2608.03838/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Compressed Chain of Thought: Efficient Reasoning Through Dense Representations](https://mlsanity.com/paper/2412.13171/) (2024)
- [Implicit Chain of Thought Reasoning via Knowledge Distillation](https://mlsanity.com/paper/2311.01460/) (2023)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [GuardReasoner: Towards Reasoning-based LLM Safeguards](https://mlsanity.com/paper/2501.18492/) (2025)
- [SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models](https://mlsanity.com/paper/2311.08370/) (2023)
- [GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners](https://mlsanity.com/paper/2509.24418/) (2025)
- [OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning](https://mlsanity.com/paper/2512.02306/) (2025)
- [Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models](https://mlsanity.com/paper/2512.05339/) (2025)
- [GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio](https://mlsanity.com/paper/2602.03328/) (2026)

## Abstract (arXiv)

Reasoning-based large language model (LLM) safeguards improve safety classification accuracy by generating explicit rationales before making decisions. However, generating explicit rationales adds substantial decoding overhead to every safety decision, while readable explanations are needed only for on-demand audits. This mismatch motivates RscriptstyleEALGscriptstyleUARD, a reliable, efficient, and auditable framework for LLM safeguards that decouples safety reasoning from rationale generation via latent reasoning. During training, a task-aligned curriculum progressively replaces explicit rationales with continuous latent reasoning under supervision from the remaining rationale text and final safety labels. In parallel, a lightweight audit decoder is trained to generate explanations conditioned on interaction text and latent states under supervision from condensed task-level rationales. At inference, the guard model makes safety decisions through continuous latent reasoning with adaptive stopping, while the audit decoder generates concise explanations when needed. Evaluations of 1B, 3B, and 8B models show that RscriptstyleEALGscriptstyleUARD improves mean F1 score by up to 1.76 points over GuardReasoner, with up to 15.7× speedups and up to 166.7× reductions in reasoning token usage during routine safety classification, while its audit decoder achieves up to 87.73% explanation acceptability under LLM-based evaluation.