Generative AI foundations · Question 47 of 60
A team uses a pure foundation LLM without further training to write test cases from a template. Instead of carrying out the instruction, the model often just continues the prompt. What explains this?
1 answer is correct. Hard Created with AI
Show answer
Answer
- B Foundation models are not tuned to follow instructions
Explanation
Foundation models are broadly pre-trained but not aligned with instructions; only instruction tuning teaches them to respond to an instruction with a fitting answer. Without adaptation, continuing the text is the more likely behaviour.