Q30 — AWS AIF-C01 Ch.3
Question 30 of 100 | ← Chapter 3
A company wants to evaluate the performance of a foundation model (FM) used for text generation. Which technique or metric satisfies these requirements?
- A. Reinforcement learning
- B. F1 score
- C. Recall-Oriented Understudy for Gisting Evaluation (ROUGE) ✓
- D. Fine-tuning
Correct Answer: C. Recall-Oriented Understudy for Gisting Evaluation (ROUGE)
Explanation
To evaluate the performance of a foundation model (FM) used for text generation, it is necessary to measure how well the generated text relates to given inputs. Recall-Oriented Understudy for Gisting Evaluation (ROUGE) is a metric specifically designed to assess overlap and similarity between generated text and reference text, thereby evaluating text generation model performance. Therefore, option C, 'Recall-Oriented Understudy for Gisting Evaluation (ROUGE)', is the appropriate technique or metric.