mlsanityData to 14 Oct 2026

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

arXiv 2505.15356 ↗First posted 21 May 2025cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 35 of its 57 references that are in the map. First posted on arXiv 21 May 2025.

Builds on

35 of 57 references.

References · 35

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  7. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
  8. 2023Teaching Large Language Models to Self-Debugcited by 988
  9. 2021Measuring Coding Challenge Competence With APPScited by 902
  10. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  11. 2023StarCoder: may the source be with you!cited by 799
  12. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
23 more
  1. 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligencecited by 331
  2. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinementcited by 247
  3. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  4. 2023Planning with Large Language Models for Code Generationcited by 182
  5. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  6. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 143
  7. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 127
  8. 2023InferFix: End-to-End Program Repair with LLMscited by 114
  9. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 111
  10. 2024Planning In Natural Language Improves LLM Search For Code Generationcited by 83
  11. 2024o1-Coder: an o1 Replication for Codingcited by 78
  12. 2024DebugBench: Evaluating Debugging Capability of Large Language Modelscited by 76
  13. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
  14. 2023CodeScore: Evaluating Code Generation by Learning Code Executioncited by 67
  15. 2024What's Wrong with Your Code Generated by Large Language Models? An Extensive Studycited by 53
  16. 2024From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debuggingcited by 46
  17. 2024LeDex: Training LLMs to Better Self-Debug and Explain Codecited by 40
  18. 2020Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesiscited by 39
  19. 2024A Deep Dive into Large Language Models for Automated Bug Localization and Repaircited by 39
  20. 2025CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generationcited by 34
  21. 2024AST-T5: Structure-Aware Pretraining for Code Generation and Understandingcited by 33
  22. 2024RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generationcited by 26
  23. 2025Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoningcited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Codecited by 6
  2. 2026FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinementcited by 1
  3. 2026LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generationcited by 0
  4. 2026EstRTL: Functional Estimation Guided RTL Code Generationcited by 0