Hi @Pragma_Tom, welcome to Prodigy!
This is often the case of "catastrophic forgetting" and becomes apparent when some new entities are added to an existing model.
Yes. The best practice is to do "pseudo-rehearsal" i.e., to use the original model to label examples and mix them through your fine-tuning updates. As for other strategies, you can check the following threads:
- Looks like a new trained model has forgotten the old entities
- New entity model ruins other entities
- Mixing in gold data to avoid catastrophic forgetting
We also published a blogpost on pseudo-rehearsal, and explains how it solves catastrophic forgetting.