LLM Evaluation

Perplexity (PPL): what it measures, how to compute it, and when it misleads

Perplexity answers one narrow question: When the true next token is revealed, how confused/uncertain is the model? It is a […]

Perplexity (PPL): what it measures, how to compute it, and when it misleads Read More »

How to Measure the Performance of LLM?

Measuring the performance of a Large Language Model (LLM) involves evaluating various aspects of its functionality, ranging from linguistic capabilities

How to Measure the Performance of LLM? Read More »