English(EN) Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

LLM驱动的自动程序修复显示出高幻觉率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

一项分析用于自动程序修复（APR）的大型语言模型（LLM）中幻觉的新研究揭示了重大问题。研究人员检查了三个LLM在832个Defects4J错误上的表现，发现只有21.0%-55.9%生成的补丁通过了开发人员编写的测试套件。研究确定在72.7%的分析案例中存在修复幻觉，其中不正确的定位和修复策略是常见原因。此外，LLM经常错误地识别触发测试用例并错误地预测行覆盖率。 AI

影响强调了LLM驱动的代码修复中的关键局限性，表明需要改进幻觉检测和缓解策略。

排序理由学术论文，详细介绍了关于LLM在自动程序修复中幻觉的研究。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 41 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了关于LLM在自动程序修复中幻觉的研究。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Xuemeng Cai, Jiakun Liu, Linhan Yang, Wei Ma, Lingxiao Jiang · 2026-09-07 04:00

更好地理解，更好地修复？一项关于 LLM 驱动的自动化程序修复中幻觉的研究

arXiv:2609.04909v1 Announce Type: cross Abstract: Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing evaluations remain largely result-centric and provide limited insight into hallucination during repair. In APR, hallucination ma…

本文如何被排名

报道来源 [1]

更好地理解，更好地修复？一项关于 LLM 驱动的自动化程序修复中幻觉的研究

相关实体

相关话题