Search papers, labs, and topics across Lattice.
College of Intelligence and Computing, Tianjin University
4
0
4
LLMs outperform traditional methods in equivalent mutant detection, achieving higher accuracy while maintaining efficiency across multiple programming languages.
Current LLMs falter in resolving LLVM compiler issues, but a new ensemble method boosts resolution rates by nearly 22%.
Coding agents may be less prone to tangled refactorings than humans, but those refactorings tank compilability.
LLMs can generate significantly better software patches by first distilling issue descriptions into structured, refined requirements.
