ConFL：基于层次引导大语言模型推理的可解释并发故障定位框架
ConFL: Explainable Concurrent Fault Localization via Hierarchy-Guided LLM Reasoning
AI总结：
ConFL是一种可解释的并发故障定位框架，通过构建并发知识库与LLM引导的层次检索，在8个Java项目的并发漏洞实验中，其MRR达0.503、MAP达0.486，性能优于同类基线方法且鲁棒性良好。
AI中文摘要：
仅从漏洞报告中定位并发漏洞极具挑战性，原因在于信息不完整、程序实体提及存在误导性，以及复杂的跨线程交互，这导致现有基于大语言模型（LLM）的方法存在推理不稳定、可解释性有限的问题。本文提出ConFL，一种可解释的并发故障定位框架，它用结构化并发知识增强LLM推理。ConFL从源代码构建并发知识库（CKB），并执行LLM引导的层次检索，逐步将搜索空间从组件缩小到交互级并发上下文。交互级领域特定语言（DSL）明确编码共享资源上的跨线程交互，使推理能聚焦于目标，无需遍历深层调用链。对来自8个大型Java项目的真实并发漏洞开展实验，结果显示ConFL显著优于最先进的基于信息检索（IR）和基于LLM的基线方法，其平均倒数排名（MRR）达0.503，平均精度均值（MAP）达0.486，同时对含噪声的漏洞报告、未见过的漏洞及不同LLM主干均具备鲁棒性。
英文摘要：
Localizing concurrent bugs from bug reports alone is challenging due to incomplete information, misleading program-entity mentions, and complex cross-thread interactions, causing existing LLM-based approaches to suffer from unstable reasoning and limited explainability. We propose ConFL, an explainable concurrent fault localization framework that augments LLM reasoning with structured concurrency knowledge. ConFL constructs a Concurrent Knowledge Base (CKB) from source code and performs LLM-guided hierarchical retrieval to progressively narrow the search space from components to interaction-level concurrency contexts. An interaction-level DSL explicitly encodes cross-thread interactions over shared resources, enabling focused reasoning without traversing deep call chains. Experiments on real-world concurrent bugs from eight large-scale Java projects show that ConFL significantly outperforms state-of-the-art IR-based and LLM-based baselines, achieving an MRR of 0.503 and a MAP of 0.486, while remaining robust to noisy bug reports, unseen bugs, and different LLM backbones.
