When fine-tuning a model on new data causes it to lose previously learned knowledge or abilities it isn't currently being trained on.
It's one of the trickier problems in fine-tuning — improving a model at one task can quietly make it worse at another it used to do well.
One of 60 free AI glossary terms
Plain-language definitions for the AI jargon you'll actually run into — no email needed, ever, for this section.
Browse the Full Glossary →