NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
confidence scores
4 papers
Cost-aware LLM-based Online Dataset Annotation
Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild
SteerConf: Steering LLMs for Confidence Elicitation