Careful Judge: Safe and Efficient Human-AI Collaborative Decision Making

stat.ML, cs.AI, cs.LG

Submitted: 2026-10-06

Updated: 2026-10-06

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Constitutional AI: Harmlessness from AI Feedback
• NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
• VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving
• Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation
• Expectation Propagation for approximate Bayesian inference
• Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
• Generating Robot Constitutions & Benchmarks for Semantic Safety
• DriveLM: Driving with Graph Visual Question Answering
• Rate-Informed Discovery via Bayesian Adaptive Multifidelity Sampling

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier