Large Language Models as Code Executors: An Exploratory Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lyu, Chenyang, Yan, Lecheng, Xing, Rui, Li, Wenxi, Samih, Younes, Ji, Tianbo, Wang, Longyue
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914968994054144
author Lyu, Chenyang
Yan, Lecheng
Xing, Rui
Li, Wenxi
Samih, Younes
Ji, Tianbo
Wang, Longyue
author_facet Lyu, Chenyang
Yan, Lecheng
Xing, Rui
Li, Wenxi
Samih, Younes
Ji, Tianbo
Wang, Longyue
contents The capabilities of Large Language Models (LLMs) have significantly evolved, extending from natural language processing to complex tasks like code understanding and generation. We expand the scope of LLMs' capabilities to a broader context, using LLMs to execute code snippets to obtain the output. This paper pioneers the exploration of LLMs as code executors, where code snippets are directly fed to the models for execution, and outputs are returned. We are the first to comprehensively examine this feasibility across various LLMs, including OpenAI's o1, GPT-4o, GPT-3.5, DeepSeek, and Qwen-Coder. Notably, the o1 model achieved over 90% accuracy in code execution, while others demonstrated lower accuracy levels. Furthermore, we introduce an Iterative Instruction Prompting (IIP) technique that processes code snippets line by line, enhancing the accuracy of weaker models by an average of 7.22% (with the highest improvement of 18.96%) and an absolute average improvement of 3.86% against CoT prompting (with the highest improvement of 19.46%). Our study not only highlights the transformative potential of LLMs in coding but also lays the groundwork for future advancements in automated programming and the completion of complex tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06667
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Models as Code Executors: An Exploratory Study
Lyu, Chenyang
Yan, Lecheng
Xing, Rui
Li, Wenxi
Samih, Younes
Ji, Tianbo
Wang, Longyue
Computation and Language
Artificial Intelligence
The capabilities of Large Language Models (LLMs) have significantly evolved, extending from natural language processing to complex tasks like code understanding and generation. We expand the scope of LLMs' capabilities to a broader context, using LLMs to execute code snippets to obtain the output. This paper pioneers the exploration of LLMs as code executors, where code snippets are directly fed to the models for execution, and outputs are returned. We are the first to comprehensively examine this feasibility across various LLMs, including OpenAI's o1, GPT-4o, GPT-3.5, DeepSeek, and Qwen-Coder. Notably, the o1 model achieved over 90% accuracy in code execution, while others demonstrated lower accuracy levels. Furthermore, we introduce an Iterative Instruction Prompting (IIP) technique that processes code snippets line by line, enhancing the accuracy of weaker models by an average of 7.22% (with the highest improvement of 18.96%) and an absolute average improvement of 3.86% against CoT prompting (with the highest improvement of 19.46%). Our study not only highlights the transformative potential of LLMs in coding but also lays the groundwork for future advancements in automated programming and the completion of complex tasks.
title Large Language Models as Code Executors: An Exploratory Study
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.06667