LLM Guardrails

LLM: Large Language Model

Overview

LLM guardrails assess prompts, generated responses, and multi-step agent actions for harmful content, policy violations, prompt injection, and unsafe tool use. Common approaches include specialized classifiers and LLM judges, hidden-state or logit probes, streaming monitors, and runtime controls such as policy-as-code, constrained decoding, and formal verification. Evaluations span moderation and jailbreak benchmarks such as HarmBench, agent-task settings such as AgentDojo and τ²-Bench, and domain-specific, multilingual, and long-context tests. The field’s central tension is balancing missed risks against over-refusal, latency, and cost, while determining whether strong benchmark scores translate into safer end-to-end systems.

Latest papers

CardsList

210 papers19 papers in the last four weeks, down 37% on the four weeks before. 0.1% of all new papers.

  1. EGS: A Complementary Safety Framework for Educational LLMs

    Nov 17, 2026Zexuan Fei, Zhengnan Guo, Yiming Luo +4LLM GuardrailsLLM Safety

  2. MedGuardBench: A Patient-Oriented Benchmark for Personalized Guardrail Development

    Nov 17, 2026Sara Khosravi, Xiaofei Wen, Majid Sarrafzadeh +1LLM GuardrailsLLM Safety Benchmarks

  3. Risk-certified prompt optimization for LLM-as-a-judge guardrails

    Nov 15, 2026Hussein Jawad, Alexandre Landeau, Guy Fleury Iradukunda +4LLM GuardrailsLanguage Model Safety Evaluation

  4. Safeguarding Agentic AI in Radiology Workflows: A Multimodel Evaluation of Rule-based and Large Language Model-based Verification

    Nov 8, 2026Semil Eminovic, Robin Schmidt, Bogdan Levita +3LLM Agent SafetyLLM Guardrails

  5. Policy Over Purpose: Auditing LLM Content Moderation of Reclaimed Slur Usage

    Nov 6, 2026Christina Chance, Kai-Wei ChangContent ModerationLLM Auditing

  6. Enmo Safety: External, Non-invasive, Model-agnostic Oversight for Off-the-Shelf Language Models

    Nov 6, 2026Mohammed Nayeem Khan, Sarun Kumar K. S., Allan Kevin T. +2LLM SafetyLLM Guardrails

  7. LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents

    Nov 2, 2026Sreehari Sankar, Debargha Ganguly, Vikash Singh +17Tool Access Control for LLM AgentsLLM Guardrails

  8. HaloGuard 2.0: An Open-Weights Constitutional Output Guard for Multilingual Response Safety

    Nov 1, 2026Ashmiya Lenin, Navaneeth Sangameswaran, Preetham SLLM GuardrailsLLM Safety Monitoring

  9. Dependable Agents Need Hard and Fuzzy Rules

    Oct 31, 2026Frederick RothLLM GuardrailsRuntime Enforcement for AI Agents

  10. C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails

    Oct 26, 2026Mintong Kang, Zhaorun Chen, Bo LiLLM SafetyLLM Guardrails

  11. KrishokTech: A Bengali Agricultural Advisory System with Explicit Authorization Controls

    Oct 23, 2026Khan Raiyan Ibne Reza, Sanjana Aktar Maria, Shakil Ahmed +2LLM GuardrailsAI-Assisted Decision Making

  12. UniGuard: Multi-View Guardrail Learning for Cross-Interface Safety Generalization

    Oct 22, 2026Viet-Thanh Pham, Thuy-Trang Vu, Junae Kim +4LLM Guardrails

  13. Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability

    Oct 22, 2026Junhao Wang, Yidou Chen, Li Lu +6LLM Safety BenchmarksMLLM Safety

  14. From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots

    Oct 22, 2026Chenhan Lyu, Kit Wislocki, Sarah Elizabeth Stoeckl +2LLM GuardrailsLLM Safety

  15. Language Is a Security Surface for Agent Guards

    Oct 15, 2026Hasan Demirkiran, Jens ErnstbergerLLM GuardrailsLLM Agent Safety

  16. Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees

    Oct 13, 2026Wenbin Hu, Huihao Jing, Haochen Shi +9LLM GuardrailsAI Agent Safety

  17. Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction

    Oct 13, 2026Md Asiful Islam, Fahmida Alam, Mihai SurdeanuLLM GuardrailsLLM Safety

  18. CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions

    Oct 13, 2026Xinyang Liao, Lingyu Li, Kaicheng Shen +4AI SafetyAI Safety Evaluation

  19. REA: From Correct LLM Judgments to Safe Decision Delivery

    Oct 12, 2026Jingxiang Meng, Aofan Liu, Yaoshuai Ma +2LLM GuardrailsLLM Safety

  20. MENTOR: Procedural Shielding of Tool-Using LLM Agents

    Oct 12, 2026Ashwani Anand, Ivi Chatzi, Ritam Raha +1LLM Agent Policy ComplianceLLM Guardrails