Discussion about this post

User's avatar
Joshua Stafford-Haworth's avatar

What prompts did you give chatGPT to mark with? Evaluating the prompt you used is fundamental to getting GPT to do anything for you, especially something as complex as marking. I'm little surprised you saw worse performance with GPT-4 being that every piece of research I've seen indicates it performs better than 3.5 in pretty much every task.

Expand full comment
Chris Wheadon's avatar

AQA are researching whether it is possible to mark short answer STEM questions with AI, but last I heard without much success.

Expand full comment
15 more comments...

No posts