用细粒度错误定位提升大模型代码修复能力
FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement
- 引入轻量诊断模型，预测代码行级可疑度以精确定位错误
- 在两个基准上平均提升8.50%修复成功率，最优提升达7.42%
- 适合需要精准代码调试的开发者与自动化修复系统使用
大语言模型生成的代码常含缺陷。现有方法依赖测试失败或自我批评等粗粒度反馈，难以定位具体错误位置。本文提出Flare框架，通过轻量级诊断模型预测代码行级可疑度，实现细粒度错误定位。考虑到诊断结果的不确定性，Flare在前k个可疑区域中搜索，并根据执行结果选择最优修复候选。在LiveCodeBench和BigCodeBench上，使用五种基线LLM进行实验，即使不进行候选搜索（k=1），Flare也优于最强基线，绝对提升达1.72%至7.42%。当搜索10个候选时，平均提升达8.50%。单独评估时，该诊断模型性能超越近期故障定位方法，证明其能提供可靠细粒度指导。
原文摘要 · Abstract (English)
Large language models often generate code with bugs. Existing methods rely on feedback signals such as test failures and self-critiques to iteratively refine the generated code. Such signals are either too coarse-grained or too high-level, which is not sufficient to inform the model where to fix the bug. In this work, we present Flare, an iterative framework with a lightweight diagnostic model that predicts line-level suspiciousness signals for bug localization and code refinement. Given the inherent uncertainty of diagnostic predictions, Flare searches over the top-k suspicious regions and selects the best candidate according to execution outcomes. Experiments on LiveCodeBench and BigCodeBench with five base LLMs show that, even without candidate search (k=1), Flare outperforms the strongest baseline with an absolute improvement from 1.72% to 7.42%. Furthermore, searching over 10 candidates yields an average improvement of 8.50% compared with no candidate search. When evaluated in isolation, our lightweight diagnostic model achieves the best performance compared with recent fault localization methods, demonstrating that it can provide reliable fine-grained guidance for code refinement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。