precision
A measure of the accuracy of positive predictions made by a model, defined as the number of true positives divided by the sum of true positives and false positives. It's an important metric in evaluating the performance of classification models.
- Credal Prediction based on Relative Likelihood
- EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
- Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport
- Fantastic Bugs and Where to Find Them in AI Benchmarks
- Increasing the Utility of Synthetic Images through Chamfer Guidance
- Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
- Model Provenance Testing for Large Language Models
- Opinion Maximization in Social Networks by Modifying Internal Opinions
- Privacy Reasoning in Ambiguous Contexts
- Probably Approximately Precision and Recall Learning
- SHAP values via sparse Fourier representation
- Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations