Prediction-Powered LLM Ranking with Adaptively Collected Human Feedback
cs.LG, stat.ME
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- PPI++: Efficient Prediction-Powered Inference
- Cost-Optimal Active AI Model Evaluation
- Prompt-Dependent Ranking of Large Language Models with Uncertainty Quantification
- CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion
- Statistical Inference for Misspecified Contextual Bandits
- Inference with the Upper Confidence Bound Algorithm
- Low Rank for Rank: Uncertainty-Aware Task-Specific LLM Ranking under Sparse Pairwise Comparisons
- Statistical Inference in Reinforcement Learning: A Selective Survey
- Inclusion Arena: An Open Platform for Evaluating Large Foundation Models with Real-World Apps
- A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth
- Statistical Inference After Adaptive Sampling for Longitudinal Data
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis