Revisit Self-Debugging with Self-Generated Tests for Code Generation

• URL: http://arxiv.org/abs/2501.12793v1
• Date: Wed, 22 Jan 2025 10:54:19 GMT
• Title: Revisit Self-Debugging with Self-Generated Tests for Code Generation
• Authors: Xiancai Chen, Zhengwei Tao, Kechi Zhang, Changzhi Zhou, Wanli Gu, Yuanpeng He, Mengdi Zhang, Xunliang Cai, Haiyan Zhao, Zhi Jin,
• Abstract summary: Self-ging with self-generated tests is a promising solution but lacks a full exploration of its limitations and practical potential. We propose two paradigms for the process: post-execution and in-execution self-ging. We find that post-execution self-ging struggles on basic problems but shows potential for improvement on competitive ones, due to the bias introduced by self-generated tests.
• Score: 18.643472696246686
• License:
• Abstract: Large language models (LLMs) have shown significant advancements in code generation, but still face challenges on tasks beyond their basic capabilities. Recently, the notion of self-debugging has been proposed to boost the performance of code generation by leveraging execution feedback from tests. Despite its promise, the availability of high-quality tests in real-world scenarios is limited. In this context, self-debugging with self-generated tests is a promising solution but lacks a full exploration of its limitations and practical potential. Therefore, we investigate its efficacy on diverse programming problems. To deepen our understanding, we propose two distinct paradigms for the process: post-execution and in-execution self-debugging. Within the scope of self-contained Python programming tasks, we find that post-execution self-debugging struggles on basic problems but shows potential for improvement on competitive ones, due to the bias introduced by self-generated tests. On the other hand, in-execution self-debugging enables LLMs to mitigate the bias by solely leveraging intermediate states during execution, thereby enhancing code generation.

Related papers

• GenX: Mastering Code and Test Generation with Execution Feedback [7.225594526057816]
  We propose a novel approach that concurrently trains a code generation model and a test generation model. We introduce two strategies for test and code data augmentation and a new scoring function for code and test ranking. The results demonstrate that our models, when iteratively trained with an increasing number of test cases and code solutions, outperform those trained on the original dataset.
  arXiv  Detail & Related papers  (2024-12-18T03:18:21Z)
• ASTER: Natural and Multi-language Unit Test Generation with LLMs [6.259245181881262]
  We describe a generic pipeline that incorporates static analysis to guide LLMs in generating compilable and high-coverage test cases. We conduct an empirical study to assess the quality of the generated tests in terms of code coverage and test naturalness.
  arXiv  Detail & Related papers  (2024-09-04T21:46:18Z)
• DOCE: Finding the Sweet Spot for Execution-Based Code Generation [69.5305729627198]
  We propose a comprehensive framework that includes candidate generation, $n$-best reranking, minimum Bayes risk (MBR) decoding, and self-ging as the core components. Our findings highlight the importance of execution-based methods and the difference gap between execution-based and execution-free methods.
  arXiv  Detail & Related papers  (2024-08-25T07:10:36Z)
• Re-ReST: Reflection-Reinforced Self-Training for Language Agents [101.22559705696885]
  Self-training in language agents can generate supervision from the agent itself. We present Reflection-Reinforced Self-Training (Re-ReST), which uses a textitreflector to refine low-quality generated samples.
  arXiv  Detail & Related papers  (2024-06-03T16:21:38Z)
• NExT: Teaching Large Language Models to Reason about Code Execution [50.93581376646064]
  Large language models (LLMs) of code are typically trained on the surface textual form of programs. We propose NExT, a method to teach LLMs to inspect the execution traces of programs and reason about their run-time behavior.
  arXiv  Detail & Related papers  (2024-04-23T01:46:32Z)
• Test-Driven Development for Code Generation [0.850206009406913]
  Large Language Models (LLMs) have demonstrated significant capabilities in generating code snippets directly from problem statements. This paper investigates if and how Test-Driven Development (TDD) can be incorporated into AI-assisted code-generation processes.
  arXiv  Detail & Related papers  (2024-02-21T04:10:12Z)
• A Static Evaluation of Code Completion by Large Language Models [65.18008807383816]
  Execution-based benchmarks have been proposed to evaluate functional correctness of model-generated code on simple programming problems. static analysis tools such as linters, which can detect errors without running the program, haven't been well explored for evaluating code generation models. We propose a static evaluation framework to quantify static errors in Python code completions, by leveraging Abstract Syntax Trees.
  arXiv  Detail & Related papers  (2023-06-05T19:23:34Z)
• Teaching Large Language Models to Self-Debug [62.424077000154945]
  Large language models (LLMs) have achieved impressive performance on code generation. We propose Self- Debugging, which teaches a large language model to debug its predicted program via few-shot demonstrations.
  arXiv  Detail & Related papers  (2023-04-11T10:43:43Z)
• Measuring Coding Challenge Competence With APPS [54.22600767666257]
  We introduce APPS, a benchmark for code generation. Our benchmark includes 10,000 problems, which range from having simple one-line solutions to being substantial algorithmic challenges. Recent models such as GPT-Neo can pass approximately 15% of the test cases of introductory problems.
  arXiv  Detail & Related papers  (2021-05-20T17:58:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.