In this video we explore the various metrics, benchmarks, and techniques available to evaluate Large Language Models such as GPT-4, Llama 2, or Falcon for a particular use case.
0:00 - Intro
0:30 - Model evaluation basics
01:21 - Usual evaluation metrics
02:08 - BLEU
02:39 - ROUGE
02:53 - Unsupervised metrics
03:19 - LLM benchmarks
03:29 - GLUE
03:46 - HellaSwag
04:00 - TriviaQA and ARC
04:20 - Domain-specific metrics
04:55 - LLM-assisted evaluation
06:33 - Airtrain
