Prompt Exploration with Prompt Regression
Published in arXiv, 2024
Recommended citation: Feffer M., Xu R., Sun Y., Yurochkin M. (2024) Prompt Exploration with Prompt Regression. arXiv (2024) https://arxiv.org/abs/2405.11083
In the advent of democratized usage of large language models (LLMs), there is a growing desire to systematize LLM prompt creation and selection processes beyond iterative trial-and-error. Prior works majorly focus on searching the space of prompts without accounting for relations between prompt variations.
Here we propose a framework, Prompt Exploration with Prompt Regression (PEPR), to predict the effect of prompt combinations given results for individual prompt elements as well as a simple method to select an effective prompt for a given use-case. We evaluate our approach with open-source LLMs of different sizes on several different tasks.
Recommended citation: Feffer M., Xu R., Sun Y., Yurochkin M. (2024) Prompt Exploration with Prompt Regression. arXiv (2024)