Look it up
AI Glossary
AI terms. Simplified.
Browse by
Evaluation & Quality
- A/B test
- Ablation study
- Accuracy
- Agent evaluation
- AI capability threshold
- AI summary drift
- Aleatoric uncertainty
- Balanced accuracy
- Benchmark
- Benchmark saturation
- Benchmarketing
- BERTScore
- BLEUBilingual Evaluation Understudy
- Brier score
- Calibration curve
- Chain-of-thought faithfulness
- Classification threshold
- Concept drift
- Confusion matrix
- Data drift
- Epistemic uncertainty
- Eval set
- EvaluationEval
- Exact match
- F1 score
- Faithfulness
- False negative
- False positive
- Golden dataset
- Ground truth
- Hallucination rate
- Human evaluation
- Human preference arena
- LLM-as-a-judge
- Log loss
- Mean absolute error
- Mean squared error
- Model confidence score
- Model drift
- Offline evaluation
- Online evaluation
- Pass rate
- pass@k
- Perplexity
- Precision
- Prediction calibration
- Prediction interval
- Recall
- Refusal rate
- Regression test
- Relevance
- Robustness
- ROC AUCArea under the receiver operating characteristic curve
- Root mean squared error
- ROUGERecall-Oriented Understudy for Gisting Evaluation
- Rubric
- Speaker attribution error
- Specificity
- Test set
- True negative
- True positive
- Uncertainty quantification
- Validation set
- Win rate
- Word error rate