Oracle 1Z0-1127-25 Exam - Topic 2 Question 11 Discussion

Actual exam question for Oracle's 1Z0-1127-25 exam

Question #: 11
Topic #: 2

Which statement accurately reflects the differences between these approaches in terms of the number of parameters modified and the type of data used?

AFine-tuning and continuous pretraining both modify all parameters and use labeled, task-specific data.

BParameter Efficient Fine-Tuning and Soft Prompting modify all parameters of the model using unlabeled data.

CFine-tuning modifies all parameters using labeled, task-specific data, whereas Parameter Efficient Fine-Tuning updates a few, new parameters also with labeled, task-specific data.

DSoft Prompting and continuous pretraining are both methods that require no modification to the original parameters of the model.

Show Suggested Answer

Suggested Answer: C

Comprehensive and Detailed In-Depth Explanation=

Fine-tuning typically involves updating all parameters of an LLM using labeled, task-specific data to adapt it to a specific task, which is computationally expensive. Parameter Efficient Fine-Tuning (PEFT), such as methods like LoRA (Low-Rank Adaptation), updates only a small subset of parameters (often newly added ones) while still using labeled, task-specific data, making it more efficient. Option C correctly captures this distinction. Option A is wrong because continuous pretraining uses unlabeled data and isn't task-specific. Option B is incorrect as PEFT and Soft Prompting don't modify all parameters, and Soft Prompting typically uses labeled examples indirectly. Option D is inaccurate because continuous pretraining modifies parameters, while SoftPrompting doesn't.

: OCI 2025 Generative AI documentation likely discusses Fine-tuning and PEFT under model customization techniques.

by Kerry at Jul 13, 2025, 08:46 AM

Limited Time Offer

25%

Off

Get Premium 1Z0-1127-25 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Galen

3 months ago

Wait, so Soft Prompting doesn't change any parameters? That's surprising!

upvoted 0 times

...

Nettie

3 months ago

I think A is misleading; not all parameters are modified in every case.

upvoted 0 times

...

Irene

4 months ago

Totally agree with C, it’s the most accurate description.

upvoted 0 times

...

Gwenn

4 months ago

D seems off; continuous pretraining usually modifies something, right?

upvoted 0 times

...

Theola

4 months ago

C is spot on! Fine-tuning really does use labeled data.

upvoted 0 times

...

Shantell

4 months ago

I feel like option A is misleading since continuous pretraining doesn't modify all parameters. I need to think more about this!

upvoted 0 times

...

Linsey

4 months ago

I practiced a question similar to this, and I recall that fine-tuning uses labeled data, so C might be the right choice.

upvoted 0 times

...

Sharmaine

5 months ago

I'm not entirely sure, but I remember something about soft prompting not changing the original parameters. Maybe option D is correct?

upvoted 0 times

...

Brittani

5 months ago

I think option C sounds familiar because it mentions fine-tuning and how it modifies all parameters, which we discussed in class.

upvoted 0 times

...

Ollie

5 months ago

This question requires a good grasp of the technical details of these fine-tuning methods. I'll need to draw on my knowledge of model parameters and data usage to determine the most accurate statement.

upvoted 0 times

...

Von

5 months ago

Okay, the key is to focus on the number of parameters modified and the type of data used. I'll make sure to compare those factors across the different approaches mentioned in the options.

upvoted 0 times

...

Janessa

5 months ago

Hmm, I'm a bit confused by the terminology here. I'll need to refresh my understanding of fine-tuning, parameter-efficient fine-tuning, and soft prompting before I can confidently answer this.

upvoted 0 times

...

Dick

6 months ago

This looks like a straightforward question about the differences between various fine-tuning techniques. I'll carefully review the options and think through the key distinctions.

upvoted 0 times

...