Câu 86: AWS Certified AI Practitioner AIF-C01

A social media company wants to use a large language model (LLM) to summarize messages. The company has chosen a few LLMs that are available on Amazon SageMaker JumpStart. The company wants to compare the generated output toxicity of these models. Which strategy gives the company the ability to evaluate the LLMs with the LEAST operational overhead?

1. A. Crowd-sourced evaluation
2. B. Automatic model evaluation — đáp án hiện tại
3. C. Model evaluation with human workers
4. D. Reinforcement learning from human feedback (RLHF)