Counting Under Disagreement: Dollar-Weighted Measurement, Selective Machine Labelling and Budgeted Human Review from Disagreeing AI Readers of Administrative Text
cs.AI, cs.LG, stat.ME
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/aeicfau/source
Terminology
Sources
- Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control
- Conformal Risk Control
- PPI++: Efficient Prediction-Powered Inference
- Efficient Inference for Noisy LLM-as-a-Judge Evaluation
- Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models
- Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements
- Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation
- Can Unconfident LLM Annotations Be Used for Confident Conclusions?
- Model-agnostic Selective Labeling with Provable Statistical Guarantees
- Model-free selective inference under covariate shift via weighted conformal p-values
- M-estimation under Two-Phase Multiwave Sampling with Applications to Prediction-Powered Inference
- Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges
- What Is Actually Being Annotated? Inter-Prompt Reliability as a Measurement Problem in LLM-Based Social Science Labeling
- Assumption-Lean and Data-Adaptive Post-Prediction Inference
- PPI is the Difference Estimator: Recognizing the Survey Sampling Roots of Prediction-Powered Inference
- Mapping Philanthropic Support of Science
- Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
- Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys
- Active Statistical Inference
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents