AIExplainer

What is an automatic evaluation?

Using software to judge the quality of a model's output.

Using software to judge the quality of a model's output. When model output is relatively straightforward, a script or program can compare the model's output to a golden response. This type of automatic evaluation is sometimes called programmatic evaluation. Metrics such as ROUGE or BLEU are often useful for programmatic evaluation. When model output is complex or has no one right answer, a separate ML program called an autorater sometimes performs the automatic evaluation. Contrast with human evaluation.

Practitioners refer to automatic evaluation when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.