LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards

• URL: http://arxiv.org/abs/2608.03838v1
• Date: Tue, 04 Aug 2026 15:47:41 GMT
• Title: LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards
• Abstract summary: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy.<n>We propose LatentGuard, an efficient and inspectable safeguard framework that brings continuous latent reasoning to guard models.
• Score: 21.146106913383868
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy. Although latent-reasoning methods reduce token generation by moving reasoning into continuous states, they remain underexplored for safety moderation and lack an inspection interface for deployment. In this paper, we propose LatentGuard, an efficient and inspectable safeguard framework that brings continuous latent reasoning to guard models. LatentGuard uses a staged curriculum to progressively compress task-aligned textual rationales into compact latent states, enabling safety verdicts to be predicted directly from continuous representations. To preserve inspectability, an isolated auxiliary decoder generates compact audit artifacts on demand, keeping rationale generation off the standard inference path. Experiments show that LatentGuard-8B improves mean weighted F1 from 83.95 to 84.91 over GuardReasoner-8B, while reducing critical-path reasoning cost from 268.56 generated rationale tokens to 1.60 latent reasoning tokens. Its audit decoder achieves an audit utility score of 85.75, demonstrating an efficient and inspectable path toward deployable LLM safeguards.

Related papers

• DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail [19.59614205209542]
  We present DT-Guard, a content safety guardrail model based on a Reasoning-Active Training, Reasoning-Free Inference paradigm.<n>The key idea is to use reasoning supervision during training while emitting only structured safety labels at inference time.
  arXiv  Detail & Related papers  (2026-07-07T14:25:05Z)
• Robust and Efficient Guardrails with Latent Reasoning [23.837448508316513]
  Reasoning-based guardrails incur substantial query latency and token overhead.<n>We propose COLAGUARD, a guardrail model that transfers multi-step safety reasoning into a continuous latent space.<n>Our results suggest latent reasoning offers a practical alternative to explicit rationale generation for deployable guardrails.
  arXiv  Detail & Related papers  (2026-05-27T20:15:22Z)
• Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection [5.902327401962825]
  We present Reflect-Guard, a method that augments LLM-based safety classifiers with chain-of-thought self-reflection capabilities.<n>Our approach distills analytical reasoning from GPT-4o-mini into structured annotations, then trains Llama-Guard-3-8B via QLoRA to generate logical self-reflections.<n>Using only 1000 training examples and updating just 0.5% of model parameters, Reflect-Guard achieves substantial improvements on two challenging benchmarks.
  arXiv  Detail & Related papers  (2026-05-24T02:58:21Z)
• Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs [51.56484100374058]
  guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency.<n>We evaluate a domain-specific multi-layer safeguard pipeline combining deterministic pattern filters, structural validation, contextual sandboxing, and session-level behavioral checks.<n>Results expose operational trade-offs: NeMo reaches 0 percent bypass at 16.22 percent FPR and roughly 1.5s latency, while Prompt Guard yields 38.48 percent bypass with 3.60 percent FPR.
  arXiv  Detail & Related papers  (2026-03-29T18:52:01Z)
• TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models [19.148124494194317]
  We propose TraceGuard, a process-guided security framework that transforms small-scale models into robust reasoning firewalls.<n>Our approach treats the reasoning trace as an untrusted payload and establishes a defense-in-depth strategy.<n>We demonstrate robustness against adaptive adversaries in a grey-box setting, establishing TraceGuard as a viable, low-latency security primitive.
  arXiv  Detail & Related papers  (2026-03-02T22:19:13Z)
• DRAFT: Task Decoupled Latent Reasoning for Agent Safety [59.46137757545185]
  We propose DRAFT (Task Decoupled Latent Reasoning for Agent Safety), a latent reasoning framework that decouples safety judgment into two trainable stages.<n>An Extractor distills the full trajectory into a compact continuous latent draft, and a Reasoner that jointly attends to the draft and the original trajectory to predict safety.<n>DRAFT consistently outperforms strong baselines, improving accuracy from 63.27% (LoRA) to 91.18% averaged over benchmarks.
  arXiv  Detail & Related papers  (2026-02-11T07:45:14Z)
• NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels [66.70287556682105]
  NExT-Guard is a training-free framework that achieves streaming safeguards by monitoring interpretable latent features from Sparse Autoencoders (SAEs)<n>It uses pretrained SAEs from publicly available base LLMs, enabling flexible, low-cost deployment without token-level supervision.<n> Experimental results show that NExT-Guard outperforms both post-hoc and streaming safeguards based on supervised training.
  arXiv  Detail & Related papers  (2026-02-10T08:54:10Z)
• ProGuard: Towards Proactive Multimodal Safeguard [48.89789547707647]
  ProGuard is a vision-language proactive guard that identifies and describes out-of-distribution (OOD) safety risks.<n>We first construct a modality-balanced dataset of 87K samples, each annotated with both binary safety labels and risk categories.<n>We then train our vision-language base model purely through reinforcement learning to achieve efficient and concise reasoning.
  arXiv  Detail & Related papers  (2025-12-29T16:13:23Z)
• ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models [23.236088751922807]
  Backdoor attacks pose a significant threat to Large Language Models (LLMs)<n>Most existing defense methods, primarily designed for classification tasks, are ineffective against the autoregressive nature and vast output space of LLMs.<n>We propose ConfGuard, a lightweight and effective detection method that monitors a sliding window of token confidences to identify sequence lock.
  arXiv  Detail & Related papers  (2025-08-02T13:38:04Z)
• GuardReasoner: Towards Reasoning-based LLM Safeguards [100.85955697211323]
  This paper proposes GuardReasoner, a new safeguard for LLMs.<n>We first create the GuardReasonerTrain dataset, which consists of 127K samples with 460K detailed reasoning steps.<n>Then, we introduce reasoning SFT to unlock the reasoning capability of guard models.<n>In this manner, GuardReasoner achieves better performance, explainability, and generalizability.
  arXiv  Detail & Related papers  (2025-01-30T17:06:06Z)
• CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment [66.72332011814183]
  CoreGuard is a computation- and communication-efficient protection method for proprietary large language models (LLMs) deployed on edge devices.<n> CoreGuard employs an efficient protection protocol to reduce computational overhead and minimize communication overhead via a propagation protocol.
  arXiv  Detail & Related papers  (2024-10-16T08:14:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.