Constructing Conversational Context
A conversational AI is being trained to answer follow-up questions. Consider the dialogue below:
Turn 1 (User): 'What is the capital of France?' Turn 1 (AI): 'The capital of France is Paris.' Turn 2 (User): 'What is its population?'
To correctly answer the user's question in Turn 2, the AI needs more than just the text 'What is its population?'. What complete input should be provided to the AI for Turn 2 to ensure it understands the question refers to Paris?
0
1
Tags
Ch.2 Generative Models - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Application in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
A language model is being tested for its conversational abilities. Below is a transcript of an interaction. Analyze the assistant's final response. What is the most likely reason for this conversational failure?
User: 'What are the main ingredients in a classic Margherita pizza?' Assistant: 'The main ingredients are San Marzano tomatoes, fresh mozzarella cheese, fresh basil, salt, and extra-virgin olive oil.' User: 'What's a good substitute for them?' Assistant: 'A good substitute for what? Please specify what you would like a substitute for.'
Constructing Conversational Context
Evaluating Training Data for Conversational AI