Q8 — AWS AIF-C01 Ch.3

Question 8 of 100 | ← Chapter 3

An insurance company is building an application that uses a large language model (LLM) for AI-powered document classification. It has a dataset of 10,000 documents with corresponding labels (e.g., 'insurance claim', 'invoice'). The model must learn the classification task and integrate knowledge from the entire dataset. Which solution minimizes prompt size while meeting these requirements?

• A. Single-shot prompting
• B. Few-shot prompting
• C. Continual pre-training
• D. Instruction-based fine-tuning ✓

Correct Answer: D. Instruction-based fine-tuning

Explanation

Instruction-based fine-tuning trains the model end-to-end on the full labeled dataset using task-specific instructions, enabling deep integration of classification logic and dataset knowledge. Unlike prompting methods—which scale poorly with 10,000 samples—or continual pre-training—which lacks task specificity—this approach achieves high accuracy with zero or minimal inference-time prompting.