model calibration

225 papers

Explore in graph

Co-occurring keywords

uncertainty quantification (1365) uncertainty estimation (639) large language model (12755) confidence calibration (173) temperature scaling (67) expected calibration error (44) language model (4573) neural network (6616) knowledge distillation (3680) label smoothing (107)

Papers

Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding WACV 2025

Interpreting the Effects of Quantization on LLMs AACL 2025

Information-theoretic Generalization Analysis for Expected Calibration Error NIPS 2024

On the Use of Anchoring for Training Vision Models NIPS 2024

Dual Calibration-based Personalised Federated Learning IJCAI 2024

Data Contamination Calibration for Black-box LLMs ACL 2024

On the calibration of powerset speaker diarization models INTERSPEECH 2024

Tug-of-War between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models COLING 2024

Watch Your Head: Assembling Projection Heads to Save the Reliability of Federated Models AAAI 2024

Interpreting Predictive Probabilities: Model Confidence or Human Label Variation? EACL 2024

Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment CVPR 2024

Schroedinger’s Threshold: When the AUC Doesn’t Predict Accuracy COLING 2024

Self-Calibrating Vicinal Risk Minimisation for Model Calibration CVPR 2024

Uncertainty Estimation in Instance Segmentation With Star-Convex Shapes WACV 2024

TEA: Test-time Energy Adaptation CVPR 2024

Design Choices for Enhancing Noisy Student Self-Training WACV 2024

LaSCal: Label-Shift Calibration without target labels NIPS 2024

CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration EACL 2024

Complex Logical Query Answering by Calibrating Knowledge Graph Completion Models ACL 2024

FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation EMNLP 2024

Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information NIPS 2024

Program-Aided Reasoners (Better) Know What They Know NAACL 2024

A Survey of Confidence Estimation and Calibration in Large Language Models NAACL 2024

Pearls from Pebbles: Improved Confidence Functions for Auto-labeling NIPS 2024

Large Language Models Must Be Taught to Know What They Don’t Know NIPS 2024