This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: 0VyckYL1sCBl6Jk7GwHC0guSqEl4CRQsUVuin2n3y1g
Cover

The Prompts We Used in Our Experiments

Written by @transcompiler | Published on 2025/3/22
TL;DR —
Check out the prompts we used during our think-and-execute experiments.

Abstract and 1. Introduction

2 Think-and-Execute

3 Experimental Setup

4 Results

5 Analysis

6 Related Work

7 Limitations and Discussion

8 Conclusion and References

A Experimental Details

B Details of Think-and-Execute

C Prompts Used in Our Experiments

D Human-written Pseudocode Prompts

E Generated Analyses

F Generated Pseudocode Prompts

G Qualitative Analysis

C Prompts Used in Our Experiments

C.1 Meta Prompt for generating an analysis (THINK: Step 2).

C.2 Meta Prompt for pseudocode prompt genration (THINK: Step 3).

C.3 Prompt for NL Planning

C.4 Prompt for EXECUTE phase

C.5 Prompt for evaluating Direct Prompting

C.6 Prompt for evaluating Zero-shot CoT

C.7 Prompt for evaluating Zero-shot PoT

C.8 Prompt for evaluating Plan-and-Solve

This paper is available on arxiv under CC BY-NC-ND 4.0 DEED license.

Authors:

(1) Hyungjoo Chae, Yonsei University;

(2) Yeonghyeon Kim, Yonsei University;

(3) Seungone Kim, KAIST AI;

(4) Kai Tzu-iunn Ong, Yonsei University;

(5) Beong-woo Kwak, Yonsei University;

(6) Moohyeon Kim, Yonsei University;

(7) Seonghwan Kim, Yonsei University;

(8) Taeyoon Kwon, Yonsei University;

(9) Jiwan Chung, Yonsei University;

(10) Youngjae Yu, Yonsei University;

(11) Jinyoung Yeo, Yonsei University.

[story continues]

Written by
@transcompiler
Transcompiler.Tech teaches you how to convert code from one programming language to another.
Topics and
tags
algorithmic-reasoning-in-lm|pseudocode-reasoning|language-model-optimization|task-level-logic|language-models|think-and-execute-framework|python-programming|think-and-execute
This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: 0VyckYL1sCBl6Jk7GwHC0guSqEl4CRQsUVuin2n3y1g