New Story
Large Language Models as Optimizers: Meta-Prompt for Prompt Optimization
by Writings, Papers and Blogs on Text ModelsSeptember 25th, 2024
Too Long; Didn't Read
This section discusses the varying styles of meta-prompts that yield the best results for different optimizer models. It highlights examples for PaLM 2-L and GPT models, detailing how generated instructions are structured to optimize the output of scorer LLMs on the GSM8K dataset.
Authors:
(1) Chengrun Yang, Google DeepMind and Equal contribution;
(2) Xuezhi Wang, Google DeepMind;
(3) Yifeng Lu, Google DeepMind;
(4) Hanxiao Liu, Google DeepMind;
(5) Quoc V. Le, Google DeepMind;
(6) Denny Zhou, Google DeepMind;
(7) Xinyun Chen, Google DeepMind and Equal contribution.
Table of Links
2 Opro: Llm as the Optimizer and 2.1 Desirables of Optimization by Llms
3 Motivating Example: Mathematical Optimization and 3.1 Linear Regression
3.2 Traveling Salesman Problem (TSP)
4 Application: Prompt Optimization and 4.1 Problem Setup
5 Prompt Optimization Experiments and 5.1 Evaluation Setup
5.4 Overfitting Analysis in Prompt Optimization and 5.5 Comparison with Evoprompt
7 Conclusion, Acknowledgments and References
B Prompting Formats for Scorer Llm
C Meta-Prompts and C.1 Meta-Prompt for Math Optimization
C.2 Meta-Prompt for Prompt Optimization
D Prompt Optimization Curves on the Remaining Bbh Tasks
E Prompt Optimization on Bbh Tasks – Tabulated Accuracies and Found Instructions
C.2 META-PROMPT FOR PROMPT OPTIMIZATION
Different optimizer models work the best on different styles of meta-prompts. Figure 3 in the main paper shows the meta-prompt for PaLM 2-L-IT; Figure 21 shows that for pre-trained PaLM 2-L; Figure 22 shows that for GPT models.
This paper is available on arxiv under CC0 1.0 DEED license.
L O A D I N G
. . . comments & more!
. . . comments & more!
