Learn Before
Evaluating Prompt Flexibility
A user wants a language model to generate a list of five creative names for a new coffee shop. They try the three different prompts listed in the case study below. Evaluate why all three prompts, despite their vast differences in structure and detail, are likely to produce relevant outputs from a well-trained language model. What does this demonstrate about the nature of instructing these models?
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Evaluation in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Rephrasing Instructions for Simplicity
Adapting LLMs to Follow Diverse Instructions via Fine-Tuning
A software development team is building a feature that allows users to ask a language model to summarize text. One developer argues for a strict input format, such as
COMMAND: SUMMARIZE, while another argues for allowing flexible, natural language inputs like'can you give me the main points?'or'what's the short version of this?'. Which of the following statements most accurately analyzes the technical feasibility of the flexible approach?Evaluating Prompt Flexibility
Example of a Standard Instruction for English-to-Chinese Translation
Evaluating Fine-Tuning Strategies for a Chatbot