Learn Before
A team is developing a system to automatically find the best instructions for a language model tasked with summarizing complex scientific papers. Their system has two main components: 1) a 'Generator' model that creates a candidate instruction, and 2) an 'Evaluator' model that reads the summary produced using that instruction and assigns it a quality score from 1 to 10. The 'Generator' then uses this score to adjust its strategy for creating future instructions. In this optimization process, wha
0
1
Tags
Ch.3 Prompting - 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
Example of an RL-based Prompt Generator
A team is developing a system to automatically find the best instructions for a language model tasked with summarizing complex scientific papers. Their system has two main components: 1) a 'Generator' model that creates a candidate instruction, and 2) an 'Evaluator' model that reads the summary produced using that instruction and assigns it a quality score from 1 to 10. The 'Generator' then uses this score to adjust its strategy for creating future instructions. In this optimization process, wha
Analyzing a Prompt Optimization System
Suitability of Reinforcement Learning for Prompt Optimization