Evaluating Training Data for Conversational AI
A developer is creating a dataset to train a language model to be a helpful, context-aware assistant. Analyze the following training data example. Explain why this specific conversational exchange is a poor example for teaching the model to maintain context across multiple turns.
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
Analysis 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