Search papers, labs, and topics across Lattice.
This paper introduces ConFL, an innovative framework for explainable concurrent fault localization that enhances LLM reasoning by integrating structured concurrency knowledge. By constructing a Concurrent Knowledge Base (CKB) and utilizing hierarchical retrieval, ConFL effectively narrows down the search space for bug localization, addressing challenges posed by incomplete information and complex cross-thread interactions. Experimental results demonstrate that ConFL outperforms existing state-of-the-art methods, achieving significant improvements in mean reciprocal rank (MRR) and mean average precision (MAP) while maintaining robustness against noisy inputs and unseen bugs.
ConFL achieves a remarkable MRR of 0.503, showcasing a leap in fault localization accuracy for concurrent bugs that traditional methods struggle with.
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.
