Learn Before
Hand-Crafted Features and Templates as Early Prompts
Before modern prompting, early NLP systems utilized hand-crafted features and predefined templates to guide models in performing specific tasks. This practice of using structured inputs to condition a model's behavior serves as a direct historical precursor to contemporary prompting methods.
0
1
Tags
Ch.4 Alignment - Foundations of Large Language Models
Foundations of Large Language Models
Computing Sciences
Foundations of Large Language Models Course
Ch.3 Prompting - Foundations of Large Language Models
Related
Hand-Crafted Features and Templates as Early Prompts
Consider an older text classification system designed to determine if a movie review is positive or negative. The system works by providing the model with a structured input like: 'Review: [movie review text]. The sentiment of this review is __.' The model is then trained to fill in the blank with either 'positive' or 'negative'. Which of the following statements best analyzes the connection between this older technique and the methods used to guide today's large-scale language models?
Connecting Past and Present NLP Interaction Methods
Analyzing the Evolution of Model Interaction
Learn After
Example of Using Formality Features in Machine Translation
An engineer is building a system to generate automated email replies for a small set of common customer support issues (e.g., password resets, billing inquiries). The system works by taking key information from the customer's email (like name and account number) and inserting it into pre-written, fixed response structures. Which statement best analyzes the primary limitation of this method if the company wanted to expand it to handle all possible customer inquiries?
Designing a Template-Based Text Generator
Analyzing an Early Machine Translation System