7 papers
An Empirical Study of LLM-Generated Specifications for VeriFast
Wen Fan, Minh Tran, Sanya Dod +5
Static verification tools can assure industrial scale software, but require significant human labor to write specifications. This is particularly true of static verifiers based on…
CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks
Danning Xie, Mingwei Zheng, Xuwei Liu +4
Large language models (LLMs) have been widely adopted across diverse domains of software engineering, such as code generation, program repair, and vulnerability detection. These ap…
Adaptive Proof Refinement with LLM-Guided Strategy Selection
Minghai Lu, Zhe Zhou, Danning Xie +3
Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual…
Validating Network Protocol Parsers with Traceable RFC Document Interpretation
Mingwei Zheng, Danning Xie, Qingkai Shi +2
Validating the correctness of network protocol implementations is highly challenging due to the oracle and traceability problems. The former determines when a protocol implementati…
Large Language Models for Validating Network Protocol Parsers
Mingwei Zheng, Danning Xie, Xiangyu Zhang
Network protocol parsers are essential for enabling correct and secure communication between devices. Bugs in these parsers can introduce critical vulnerabilities, including memory…
How Effective are Large Language Models in Generating Software Specifications?
Danning Xie, Byungwoo Yoo, Nan Jiang +4
Software specifications are essential for many Software Engineering (SE) tasks such as bug detection and test generation. Many existing approaches are proposed to extract the speci…