基于 LLM 的静态可空性错误修复

Computer Science > Software Engineering arXiv:2507.20674 (cs) [Submitted on 28 Jul 2025 (v1), last revised 22 Sep 2026 (this version, v3)] Title:LLM-Based Repair of Static Nullability Errors Authors:Nima Karimipour, Pascal Joos, Michael Pradel, Martin Kellogg, Manu Sridharan View a PDF of the paper titled LLM-Based Repair of Static Nullability Errors, by Nima Karimipour and Pascal Joos and Michael Pradel and Martin Kellogg and Manu Sridharan View PDF HTML (experimental) Abstract:Modern Java projects increasingly adopt static analysis tools that prevent null-pointer exceptions by treating nullness as a type property. However, integrating such tools into large, existing codebases remains a significant challenge. While annotation inference can eliminate many errors automatically, a subset of residual errors $-$ typically a mix of real bugs and false positives $-$ often persists and can only be resolved via code changes. Manually addressing these errors is tedious and error-prone. Large language models (LLMs) offer a promising path toward automating these repairs, but naively prompted LLMs often generate incorrect, contextually inappropriate edits. We present NullRepair, a system that integrates LLMs into a structured workflow for resolving the errors from a nullability checker. NullRepair's decision process follows a flowchart derived from manual analysis of 200 real-world errors. It leverages static analysis to identify safe and unsafe usage regions of symbols, using error-free usage examples to contextualize model prompts. Patches are generated through an iterative interaction with the LLM that incorporates project-wide context and decision logic. Our evaluation on 12 real-world Java projects shows that NullRepair resolves 63% of the 1,119 nullability errors that remain after applying a state-of-the-art annotation inference technique. Unlike two baselines (single-shot prompt and mini-SWE-agent), NullRepair also largely preserves program semantics, with all unit tests passing in 10/12 projects after applying every edit proposed by NullRepair, and 98% or more tests passing in the remaining two projects. Subjects: Software Engineering (cs.SE); Programming Languages (cs.PL) Cite as: arXiv:2507.20674 [cs.SE] (or arXiv:2507.20674v3 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2507.20674 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Pascal Joos [view email] [v1] Mon, 28 Jul 2025 09:55:04 UTC (113 KB) [v2] Fri, 6 Feb 2026 10:34:05 UTC (1,387 KB) [v3] Tue, 22 Sep 2026 11:51:48 UTC (863 KB) Full-text links: Access Paper: View a PDF of the paper titled LLM-Based Repair of Static Nullability Errors, by Nima Karimipour and Pascal Joos and Michael Pradel and Martin Kellogg and Manu Sridharan View PDF HTML (experimental) TeX Source view license Current browse context: cs.SE new | recent | 2025-07 Change to browse by: cs cs.PL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)