@inproceedings{tran-etal-2026-program,
    title = "Program Structure-aware Language Models: Targeted Software Testing beyond Textual Semantics",
    author = "Tran, Khang  and
      Nguyen, Khoa  and
      Borcea, Cristian  and
      Phan, Hai",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.findings-acl.540/",
    pages = "11113--11126",
    ISBN = "979-8-89176-395-1",
    abstract = "Recent advances in large language models for test case generation have improved branch coverage via prompt-engineered mutations. However, they still lack principled mechanisms for steering models toward specific high-risk execution branches, limiting their effectiveness for discovering subtle bugs and security vulnerabilities. We propose $GLMTest$, the first program structure-aware LLM framework for targeted test case generation that seamlessly integrates code property graphs and code semantics using a graph neural network and a language model to condition test case generation on execution branches. This structured conditioning enables controllable and branch-targeted test case generation, thereby potentially enhancing bug and security risk discovery. Experiments on real-world projects show that $GLMTest$ built on a Qwen2.5-Coder-7B-Instruct model improves branch accuracy from 27.4{\%} to 50.2{\%} on TestGenEval benchmark compared with state-of-the-art LLMs, i.e., Claude-Sonnet-4.5 and GPT-4o-mini."
}