Metraipolis › archive › dc_23215ae376fc

ConFL: Explainable Concurrent Fault Localization via Hierarchy-Guided LLM Reasoning — arXiv:2608.02974

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02974
License (as archived)
CC0-1.0
Archived
2026-10-31T12:43:24.618Z
SHA-256 of the archived text
ef972ce39283adb3b25fe6349b324f942eaf70c130cf1c05f8ea939562c02cd3
Stable URL of this page
https://metraipolis.com/documento/dc_23215ae376fc

How to cite

ConFL: Explainable Concurrent Fault Localization via Hierarchy-Guided LLM Reasoning — arXiv:2608.02974 — arXiv (en), https://arxiv.org/abs/2608.02974 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_23215ae376fc (Metraipolis archive dc_23215ae376fc, sha256 ef972ce39283adb3b25fe6349b324f942eaf70c130cf1c05f8ea939562c02cd3)
BibTeX
@misc{dc23215ae376fc,
  title = {ConFL: Explainable Concurrent Fault Localization via Hierarchy-Guided LLM Reasoning — arXiv:2608.02974},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02974},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_23215ae376fc; sha256 ef972ce39283adb3b25fe6349b324f942eaf70c130cf1c05f8ea939562c02cd3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02974. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-05 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.02974 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:33:04.210Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).