Matchability-Aware Conformal Prediction for Open-Ended Language Model Generation
stat.ML, cs.CL, cs.LG, stat.ME
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/Unco3892/caelum
Project page: https://unco3892.github.io/caelum
Terminology
Sources
- GPT-4 Technical Report
- LLaMA: Open and Efficient Foundation Language Models
- Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
- Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees
- Measuring short-form factuality in large language models
- Qwen3 Technical Report
- Conformal Prediction with Large Language Models for Multi-Choice Question Answering
- JUCAL: Jointly Calibrating Aleatoric and Epistemic Uncertainty in Classification Tasks
- Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference