Exact Match Ratio (EM)
Evaluation metric for QA tasks measuring the fraction of predictions that exactly match the ground truth.
Evaluation metric for QA tasks measuring the fraction of predictions that exactly match the ground truth.
Systems for augmenting LLMs with search, retrieval, or code execution to ground answers in fresh data.
Techniques that make model predictions interpretable, e.g., SHAP, LIME, saliency maps.
Quantitative measure of model performance, such as accuracy, F1, BLEU, ROUGE, or perplexity.
Regularization technique that halts training when validation performance stops improving.
Measure of uncertainty in a probability distribution; also used to describe randomness in cryptographic keys.
Combining multiple models to improve accuracy and robustness, e.g., bagging, boosting.
Neural network component that maps inputs to latent representations; often bidirectional in Transformers.
Model that converts inputs to vector embeddings used for search, clustering, or retrieval‑augmented generation.
Per‑unit cost of gas; the base fee is burned under EIP‑1559 while tips incentivize inclusion.