Introduction to machine learning · Question 51 of 60
Which statements about the relationship between fine-tuning and RAG are correct?
3 answers are correct. Hard
Show answer
Answer
- B A pretrained model can be adapted via RAG, via fine-tuning or with both
- C In fine-tuning, performance is evaluated and further fine-tuning is performed if necessary until the acceptance criteria are met
- E Fine-tuning requires much less training data than training from scratch
Explanation
A pretrained model can combine RAG, fine-tuning or both. Compared with training from scratch, fine-tuning saves a lot of training data and effort; after training, performance is evaluated and further fine-tuning may be performed. RAG, by contrast, does not change the model.