Glossary term
Glossary term
Architecture
A probabilistic model makes decisions or predictions based on the likelihood of different outcomes. Instead of producing one correct answer, it weighs possibilities and selects the most likely one, making it useful for language, reasoning, and uncertain scenarios.
Naive Bayes and Bayesian Networks are classic probabilistic models still used in spam filtering and risk scoring.
All modern LLMs sample next tokens probabilistically, with temperature controlling randomness.
Google DeepMind's AlphaFold combines probabilistic modelling with deep learning for protein structure prediction.