5 papers
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
Yuling Shi, Songsong Wang, Chengcheng Wan +2
While large language models have made significant strides in code generation, the pass rate of the generated code is bottlenecked on subtle errors, often requiring human interventi…
An Empirical Study of Reasoning Steps in Thinking Code LLMs
Haoran Xue, Gias Uddin, Song Wang
Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accur…
PAGENT: Learning to Patch Software Engineering Agents
Haoran Xue, Gias Uddin, Song Wang
LLM Agents produce patches automatically to resolve an issue. However, they can generate inaccurate patches. Little is known about the root causes behind those failed patches or ho…
The Ripple Effect of Vulnerabilities in Maven Central: Prevalence, Propagation, and Mitigation Challenges
Ehtisham Ul Haq, Song Wang, Robert S. Allison
The widespread use of package managers like Maven has accelerated software development but has also introduced significant security risks due to vulnerabilities in dependencies. In…
ChatGPT Inaccuracy Mitigation during Technical Report Understanding: Are We There Yet?
Salma Begum Tamanna, Gias Uddin, Song Wang +2
Hallucinations, the tendency to produce irrelevant/incorrect responses, are prevalent concerns in generative AI-based tools like ChatGPT. Although hallucinations in ChatGPT are stu…