A research team is trying to find the optimal prompt for a language model to generate high-quality Python code. The prompts are sequences of discrete words, and evaluating the quality of the code generated by any single prompt is a time-consuming, computationally expensive process. Given these constraints, which of the following classic optimization approaches would be the LEAST suitable for this task?
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
Evolutionary Computation for Prompt Optimization
Automating Prompt Discovery for Marketing Slogans
A research team is treating the task of finding the best prompt for summarizing legal documents as a formal optimization problem. Match each component of a classic optimization framework to its corresponding element in this prompt optimization scenario.
A research team is trying to find the optimal prompt for a language model to generate high-quality Python code. The prompts are sequences of discrete words, and evaluating the quality of the code generated by any single prompt is a time-consuming, computationally expensive process. Given these constraints, which of the following classic optimization approaches would be the LEAST suitable for this task?