NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Weiming, Li, Qingyao, Dai, Xinyi, Chen, Jizheng, Du, Kounianhua, Liu, Weiwen, Wang, Yasheng, Tang, Ruiming, Yu, Yong, Zhang, Weinan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917048685166592
author Zhang, Weiming
Li, Qingyao
Dai, Xinyi
Chen, Jizheng
Du, Kounianhua
Liu, Weiwen
Wang, Yasheng
Tang, Ruiming
Yu, Yong
Zhang, Weinan
author_facet Zhang, Weiming
Li, Qingyao
Dai, Xinyi
Chen, Jizheng
Du, Kounianhua
Liu, Weiwen
Wang, Yasheng
Tang, Ruiming
Yu, Yong
Zhang, Weinan
contents Debugging is a critical aspect of LLM's coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programming errors that require a deeper understanding of algorithmic logic. Recent advancements in large language models (LLMs) have shifted attention toward leveraging natural language reasoning to enhance code-related tasks. However, two fundamental questions remain unanswered: What type of natural language format is most effective for debugging tasks? And what specific benefits does natural language reasoning bring to the debugging process? In this paper, we introduce NL-DEBUGGING, a novel framework that employs natural language as an intermediate representation to improve code debugging. By debugging at a natural language level, we demonstrate that NL-DEBUGGING outperforms traditional debugging methods and enables a broader modification space through direct refinement guided by execution feedback. Our findings highlight the potential of natural language reasoning to advance automated code debugging and address complex programming challenges.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15356
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging
Zhang, Weiming
Li, Qingyao
Dai, Xinyi
Chen, Jizheng
Du, Kounianhua
Liu, Weiwen
Wang, Yasheng
Tang, Ruiming
Yu, Yong
Zhang, Weinan
Computation and Language
Debugging is a critical aspect of LLM's coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programming errors that require a deeper understanding of algorithmic logic. Recent advancements in large language models (LLMs) have shifted attention toward leveraging natural language reasoning to enhance code-related tasks. However, two fundamental questions remain unanswered: What type of natural language format is most effective for debugging tasks? And what specific benefits does natural language reasoning bring to the debugging process? In this paper, we introduce NL-DEBUGGING, a novel framework that employs natural language as an intermediate representation to improve code debugging. By debugging at a natural language level, we demonstrate that NL-DEBUGGING outperforms traditional debugging methods and enables a broader modification space through direct refinement guided by execution feedback. Our findings highlight the potential of natural language reasoning to advance automated code debugging and address complex programming challenges.
title NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging
topic Computation and Language
url https://arxiv.org/abs/2505.15356