Liu, Kaibo; Chen, Zhenpeng; Liu, Yiyang; Zhang, Jie M; Harman, Mark; Han, Yudong; Ma, Yun; ... Huang, Gang; + view all Liu, Kaibo; Chen, Zhenpeng; Liu, Yiyang; Zhang, Jie M; Harman, Mark; Han, Yudong; Ma, Yun; Dong, Yihong; Li, Ge; Huang, Gang; - view fewer (2025) LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs. In: Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Taher Pilehvar, Mohammad, (eds.) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics. (pp. pp. 430-440). Association for Computational Linguistics (ACL): Vienna, Austria.

Preview

Text Harman_2025 .acl-long.20.pdf Download (6MB) | Preview

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×, 2.65×, and 1.66× those of the state-of-the-art baselines, respectively. Code and data used are available at https://github.com/RinCloud/TrickCatcher/.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item