LLM-Based Repair of Static Nullability Errors

2025-07-28

AI Summary

Modern Java projects widely adopt nullability annotations for static analysis to prevent NullPointerExceptions; however, integrating them into large legacy codebases leaves numerous residual mixed errors—comprising both genuine defects and false positives—requiring manual intervention after annotation inference. Method: We propose NullRepair, the first automated repair system that synergistically combines static analysis, whole-project contextual modeling, and structured LLM prompting. It identifies symbol usage regions as safe or unsafe and leverages multi-granularity context (method-, class-, and package-level) to guide an LLM in generating semantics-preserving repair patches. Contribution/Results: Evaluated on 12 real-world Java projects, NullRepair repairs 72% of residual nullability errors on average. Unit tests pass at 100% for 10 projects and ≥98% for the remaining two—significantly outperforming baseline LLM-only approaches.

Technology Category

• Natural Language Processing: Safety and Robustness
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

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 persist 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. Resolving a nullability error demands a deep understanding of how a symbol is used across the codebase, often spanning methods, classes, and packages. 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 an average of 72% of the errors that remain after applying a state-of-the-art annotation inference technique. Unlike a naively-prompted LLM, 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.

Problem

• Automating repair of persistent null-pointer errors in Java
• Improving LLM-based fixes for contextually complex nullability issues
• Reducing manual effort in resolving static analysis false positives

Innovation

• LLM-based structured workflow for nullability errors
• Static analysis identifies safe and unsafe symbol usage
• Iterative LLM interaction with project-wide context