Publications (7)
Knowledge Matters: Injecting Project and Testing Knowledge into LLM-based Unit Test Generation
Anji Li, Mingwei Liu, Zhenxi Chen +5
Automated unit test generation using large language models (LLMs) holds great promise but often struggles with generating tests that are both correct and maintainable in real-world…
EvolMathEval: Towards Evolvable Benchmarks for Mathematical Reasoning via Evolutionary Testing
Shengbo Wang, Mingwei Liu, Zike Li +4
The rapid advancement of Large Language Models (LLMs) poses a significant challenge to existing mathematical reasoning benchmarks. However, these benchmarks tend to become easier o…
Unseen-Codebases-Domain Data Synthesis and Training Based on Code Graphs
Guangsheng Ou, Qiming Zhang, Sirong Chen +9
In the context of newly release software frameworks, large language models (LLMs) often exhibit poor performance and a high rate of hallucination, as they are not exposed to such e…
FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks
Dekun Dai, MingWei Liu, Anji Li +5
Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated c…
iJTyper: An Iterative Type Inference Framework for Java by Integrating Constraint- and Statistically-based Methods
Zhixiang Chen, Anji Li, Neng Zhang +3
Inferring the types of API elements in incomplete code snippets (e.g., those on Q&A forums) is a prepositive step required to work with the code snippets. Existing type inference m…
A Preliminary Study on the Robustness of Code Generation by Large Language Models
Zike Li, Mingwei Liu, Anji Li +4
Robustness is a critical factor for reliable code generation by large language models, yet most evaluations focus on correctness and overlook key issues such as missing input valid…
Are Decoder-Only Large Language Models the Silver Bullet for Code Search?
Yuxuan Chen, Mingwei Liu, Guangsheng Ou +4
Code search is essential for code reuse, allowing developers to efficiently locate relevant code snippets. The advent of powerful decoder-only Large Language Models (LLMs) has revo…