14 papers
Answer Is Cheap, Show Me the Evidence! Augmenting Automated Vulnerability Assessment with Evidence
Shengyi Pan, Zelong Zheng, Jiayuan Zhou +3
Software vulnerability (SV) assessment helps prioritize remediation by characterizing reported vulnerabilities. Existing automated methods predict assessment results from SV report…
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…
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…
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…
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…
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…
Clean Code, Better Models: Enhancing LLM Performance with Smell-Cleaned Dataset
Zhipeng Xue, Xiaoting Zhang, Zhipeng Gao +4
The Large Language Models (LLMs) have demonstrated great potential in code-related tasks. However, most research focuses on improving the output quality of LLMs (e.g., correctness)…
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…
Verified Lifting of Deep learning Operators
Qi Zhan, Xing Hu, Xin Xia +1
Deep learning operators are fundamental components of modern deep learning frameworks. With the growing demand for customized operators, it has become increasingly common for devel…
SelfPiCo: Self-Guided Partial Code Execution with LLMs
Zhipeng Xue, Zhipeng Gao, Shaohua Wang +3
Code executability plays a vital role in software debugging and testing (e.g., detecting runtime exceptions or assertion violations). However, code execution, especially partial or…
Exploring the Capabilities of LLMs for Code Change Related Tasks
Lishui Fan, Jiakun Liu, Zhongxin Liu +3
Developers deal with code-change-related tasks daily, e.g., reviewing code. Pre-trained code and code-change-oriented models have been adapted to help developers with such tasks. R…
Automating Zero-Shot Patch Porting for Hard Forks
Shengyi Pan, You Wang, Zhongxin Liu +3
Forking is a typical way of code reuse, which provides a simple way for developers to create a variant software (denoted as hard fork) by copying and modifying an existing codebase…
PS: Precise Patch Presence Test based on Semantic Symbolic Signature
Qi Zhan, Xing Hu, Zhiyang Li +3
During software development, vulnerabilities have posed a significant threat to users. Patches are the most effective way to combat vulnerabilities. In a large-scale software syste…
ACWRecommender: A Tool for Validating Actionable Warnings with Weak Supervision
Zhipeng Xue, Zhipeng Gao, Xing Hu +1
Static analysis tools have gained popularity among developers for finding potential bugs, but their widespread adoption is hindered by the accomnpanying high false alarm rates (up…