Generative AI foundations · Question 16 of 60
What can a multimodal LLM do that a text-only LLM cannot?
1 answer is correct. Easy Created with AI
Show answer
Answer
- B Process several kinds of data such as text, images and sound
Explanation
Multimodal LLMs extend the transformer to further modalities such as images, sound and video. Text-only LLMs can also handle several languages; that is not a separate modality.