Learn Before
Example

Healthcare Assistant Chatbot as a Multi-Round Prediction Problem

An application of a multi-round prediction problem is an LLM that functions as a healthcare assistant chatbot. This use case requires the model to maintain a coherent and context-aware conversation with a user over several interactions to provide assistance. The following is an example of such a conversation:

  • User: I’ve been feeling very tired lately.
  • Chatbot: I’m sorry to hear that. Besides feeling tired, have you noticed any other symptoms?
  • User: Yes, I’m also experiencing headaches frequently.
  • Chatbot: How long have these symptoms been going on?
  • User: About a week now.
  • Chatbot: It might be good to check in with a healthcare professional. Would you like help setting up an appointment?
  • User: Yes, please. Can it be after work hours?
  • Chatbot: Sure, I can arrange that. There are slots available next Wednesday and Thursday after 5 PM. Which day works better for you?

0

1

Updated 2026-05-01

Contributors are:

Who are from:

Tags

Ch.4 Alignment - Foundations of Large Language Models

Foundations of Large Language Models

Computing Sciences

Foundations of Large Language Models Course

Related