Optimizing Scoring Models: Effective Prompting Formats

This section illustrates the use of prompting formats for scorer large language models (LLMs), focusing on examples of Q_begin, Q_end, and A_begin formats when the “QA” pattern is present. It emphasizes that the “QA” pattern is eliminated in instruction-tuned scorer models like text-bison when employing the Q_begin and Q_end formats.


This content originally appeared on HackerNoon and was authored by Writings, Papers and Blogs on Text Models

:::info 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.

:::

Abstract and 1. Introduction

2 Opro: Llm as the Optimizer and 2.1 Desirables of Optimization by Llms

2.2 Meta-Prompt Design

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

4.2 Meta-Prompt Design

5 Prompt Optimization Experiments and 5.1 Evaluation Setup

5.2 Main Results

5.3 Ablation Studies

5.4 Overfitting Analysis in Prompt Optimization and 5.5 Comparison with Evoprompt

6 Related Work

7 Conclusion, Acknowledgments and References

A Some Failure Cases

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

B PROMPTING FORMATS FOR SCORER LLM

Figure 14, 15, and 16 show examples of the Qbegin, Qend, and Abegin prompting formats when the “QA” pattern is present. The “QA” pattern is eliminated when prompting instruction-tuned scorer models like text-bison with the Qbegin and Q_end formats (Figure 17 and 18).

Figure 14: The Q_begin prompting format on a GSM8K test exemplar with the "QA" pattern.

Figure 15: The Q_end prompting format on a GSM8K test exemplar with the "QA" pattern.

Figure 16: The A_begin prompting format on a GSM8K test exemplar.

Figure 17: The Q_begin prompting format on a GSM8K test exemplar without the "QA" pattern.

Figure 18: The Q_end prompting format on a GSM8K test exemplar without the "QA" pattern.

\

:::info This paper is available on arxiv under CC0 1.0 DEED license.

:::

\


This content originally appeared on HackerNoon and was authored by Writings, Papers and Blogs on Text Models


Print Share Comment Cite Upload Translate Updates
APA

Writings, Papers and Blogs on Text Models | Sciencx (2024-09-25T09:30:20+00:00) Optimizing Scoring Models: Effective Prompting Formats. Retrieved from https://www.scien.cx/2024/09/25/optimizing-scoring-models-effective-prompting-formats/

MLA
" » Optimizing Scoring Models: Effective Prompting Formats." Writings, Papers and Blogs on Text Models | Sciencx - Wednesday September 25, 2024, https://www.scien.cx/2024/09/25/optimizing-scoring-models-effective-prompting-formats/
HARVARD
Writings, Papers and Blogs on Text Models | Sciencx Wednesday September 25, 2024 » Optimizing Scoring Models: Effective Prompting Formats., viewed ,<https://www.scien.cx/2024/09/25/optimizing-scoring-models-effective-prompting-formats/>
VANCOUVER
Writings, Papers and Blogs on Text Models | Sciencx - » Optimizing Scoring Models: Effective Prompting Formats. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2024/09/25/optimizing-scoring-models-effective-prompting-formats/
CHICAGO
" » Optimizing Scoring Models: Effective Prompting Formats." Writings, Papers and Blogs on Text Models | Sciencx - Accessed . https://www.scien.cx/2024/09/25/optimizing-scoring-models-effective-prompting-formats/
IEEE
" » Optimizing Scoring Models: Effective Prompting Formats." Writings, Papers and Blogs on Text Models | Sciencx [Online]. Available: https://www.scien.cx/2024/09/25/optimizing-scoring-models-effective-prompting-formats/. [Accessed: ]
rf:citation
» Optimizing Scoring Models: Effective Prompting Formats | Writings, Papers and Blogs on Text Models | Sciencx | https://www.scien.cx/2024/09/25/optimizing-scoring-models-effective-prompting-formats/ |

Please log in to upload a file.




There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.