LLM Evaluation Techniques in Practice

edX MOOC / Non-credit USD 30
Enroll now →
LLM Evaluation Techniques in Practice

About this course

Learn practical techniques for evaluating large language models across question answering and text generation tasks. Compare model behavior using reference-based metrics, semantic similarity, log probabilities, and perplexity.

What you'll learn

  • understand reference-based metrics
  • evaluate model behavior using semantic similarity
  • compute log probabilities and perplexity

Course objectives

  • develop skills for practical evaluation of language models
  • compare model performance across tasks

Skills you'll gain

machine learningmodel evaluationdata analysislanguage modelsquestion answeringevaluation techniquestext generationsemantic similaritylog probabilitiesperplexity

Related courses

Data Science Foundations
USD 49
Machine Learning for Trading
USD 49
Internet of Things and AI Cloud
USD 49
DataPrep for H2O Driverless AI
USD 49
Fundamentals of Natural Language Processing
USD 49
Statistical Learning for Data Science
USD 49
Generative AI for NLP with PyTorch Capstone Project
USD 49
Cloud Machine Learning Engineering and MLOps
USD 49
Course details are provided by the platform and may change — always confirm on the provider's site. Links may be affiliate links.