AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/unslothai/unsloth
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Llama-Nemotron: Efficient Reasoning Models
- Thinkless: LLM Learns When to Think
- Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- DynaGuard: A Dynamic Guardian Model With User-Defined Policies
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
- Reasoning as an Adaptive Defense for Safety
- GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
- GuardReasoner: Towards Reasoning-based LLM Safeguards
- A Holistic Approach to Undesired Content Detection in the Real World
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- gpt-oss-120b & gpt-oss-20b Model Card
- Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
- Safety Alignment Should Be Made More Than Just a Few Tokens Deep
- GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection
- Proximal Policy Optimization Algorithms
- SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
- Gemma 4 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems