Learn Before
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
Tags
Ch.4 Alignment - Foundations of Large Language Models
Foundations of Large Language Models
Computing Sciences
Foundations of Large Language Models Course
Related
Comparison of Single-Round vs. Multi-Round Prediction Problems
Healthcare Assistant Chatbot as a Multi-Round Prediction Problem
Training Objective for Multi-Round Dialogue Models
Conditional Log-Probability of a Response in Multi-Round Dialogue
A user is interacting with a language model to plan a vacation. Analyze the following conversation:
Turn 1:
- User: "I want to book a flight to a warm destination for December."
- Model: "That sounds lovely! To help you, could you tell me which continent you're interested in?"
Turn 2:
- User: "Let's focus on South America."
- Model: "Excellent choice for December. Based on that, I recommend Brazil or Colombia. Do you have a preference?"
To generate its response in Turn 2, which of the following sets of information must the model have processed to ensure its suggestion is both relevant and coherent?
Analysis of a Conversational Failure
A user is interacting with a customer support model for an e-commerce site. Consider the following two-turn conversation:
Turn 1:
- User: "Hi, I ordered a blue t-shirt last week, order #12345. The tracking says it was delivered, but I haven't received it."
- Model: "I'm sorry to hear that. Let me check the details for order #12345. I see it was marked as delivered two days ago. Could you please confirm your shipping address is 123 Main St, Anytown?"
Turn 2:
- User: "Yes, that's the correct address. What should I do next?"
Given this history, which of the following responses from the model would be the most effective and contextually appropriate for the next turn?
Learn After
Chatbot Interaction Analysis
A user is interacting with a chatbot designed to help with medical queries. Arrange the following conversational turns into the most logical and coherent sequence.
A user is interacting with a healthcare assistant chatbot. Review the conversation below:
User: 'I have a sharp pain in my lower back that started this morning.' Chatbot: 'I’m sorry to hear that. On a scale of 1 to 10, how severe is the pain?' User: 'It’s about a 7. It gets worse when I try to stand up straight.'
Which of the following is the most effective next response for the chatbot to continue the multi-round interaction appropriately?