@inproceedings{liu-etal-2025-llm,
    title = "{LLM}-Powered Test Case Generation for Detecting Bugs in Plausible Programs",
    author = "Liu, Kaibo  and
      Chen, Zhenpeng  and
      Liu, Yiyang  and
      Zhang, Jie M.  and
      Harman, Mark  and
      Han, Yudong  and
      Ma, Yun  and
      Dong, Yihong  and
      Li, Ge  and
      Huang, Gang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.20/",
    pages = "430--440",
    ISBN = "979-8-89176-251-0",
    abstract = "Detecting tricky bugs in plausible programs, those that pass existing test suites yet still contain bugs, remains a significant challenge in software testing. To address this problem, we propose TrickCatcher, an LLM-powered approach to generating test cases for uncovering bugs in plausible programs. TrickCatcher operates in three stages: First, it uses an LLM to generate program variants based on the program under test (PUT) and its specification. Second, it employs an LLM to construct an input generator from the specification for producing test inputs. Finally, these inputs are executed on both the PUT and its program variants to detect inconsistencies in their outputs. We evaluate TrickCatcher on two datasets, TrickyBugs and EvalPlus, which include 366 human-written and 151 AI-generated plausible programs with tricky bugs. TrickCatcher achieves recall, precision, and F1 scores that are 1.80{\texttimes}, 2.65{\texttimes}, and 1.66{\texttimes} those of the state-of-the-art baselines, respectively. Code and data used are available at https://github.com/RinCloud/TrickCatcher/."
}