8 papers
Automating Just-In-Time Python Type Annotation Updating
Zhipeng Xue, Zhipeng Gao, Xing Hu +3
Type annotations are more and more popular in Python projects to avoid type errors caused by Python's dynamic typing feature. However, when developers change source code, these typ…
ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision?
Lishui Fan, Mouxiang Chen, Tingwei Zhu +4
Code generation is important in software engineering, and Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm to improve it through execution-based feedbac…
Mitigating Implicit Inconsistencies in Patch Porting
Shengyi Pan, Zhongxin Liu, Jiayuan Zhou +3
Promptly porting patches from a source codebase to its variants (e.g., forks and branches) is essential for mitigating propagated defects and vulnerabilities. Recent studies have e…
Verify Implementation Equivalence of Large Models
Qi Zhan, Xing Hu, Xin Xia +1
Verifying whether two implementations of the same large model are equivalent across frameworks is difficult in practice. Even when they realize the same computation, their graphs m…
FGIT: Fault-Guided Fine-Tuning for Code Generation
Lishui Fan, Zhongxin Liu, Haoye Wang +3
Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) so…
Actionable Warning Is Not Enough: Recommending Valid Actionable Warnings with Weak Supervision
Zhipeng Xue, Zhipeng Gao, Tongtong Xu +3
The use of static analysis tools has gained increasing popularity among developers in the last few years. However, the widespread adoption of static analysis tools is hindered by t…