Training Alignment Auditors via Reinforcement Learning
cs.AI, cs.LG
Submitted: 2026-08-26
Updated: 2026-08-26
Code: https://github.com/paulrosu11/training-auditing-agents-public
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
- Jailbreaking Black Box Large Language Models in Twenty Queries
- Deep reinforcement learning from human preferences
- DeepSeek-V3 Technical Report
- Gemma 3 Technical Report
- The Llama 3 Herd of Models
- Alignment faking in large language models
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Eliciting Language Model Behaviors with Investigator Agents
- Auditing language models for hidden objectives
- Training language models to follow instructions with human feedback
- AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
- Clio: Privacy-Preserving Insights into Real-World AI Use
- Auditing Games for Sandbagging
- Hermes 4 Technical Report
- Qwen2.5 Technical Report
- WildChat: 1M ChatGPT Interaction Logs in the Wild
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection