MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/tatsu-lab/stanford_alpaca
Terminology
Sources
- Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
- Continual Safety Alignment via Gradient-Based Sample Selection
- Constitutional AI: Harmlessness from AI Feedback
- Inference-Time Intervention in Large Language Models for Reliable Requirement Verification
- The Llama 3 Herd of Models
- WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
- From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
- Superficial Safety Alignment Hypothesis
- NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Terms
- Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
- Defending Against Prompt Injection with DataFilter
- Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods
- Qwen3 Technical Report
- LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
- EADC: Evaluation of Advanced and Deep-level Compliance in Large Language Models
- Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention
- When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
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