55 citations · 81 across the 7 of their papers we have counts for
8 papers · 1 filter
Benchmarking and Enhancing Design-Aware Code Review in the Linux Kernel
Zhenhao Zhou, Kai Yu, Ying Wang +5
Code review often requires reasoning beyond local correctness. In mature software systems, reviewers must recognize design trade-offs introduced by a proposed change, compare alter…
Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution
Kai Yu, Zhenhao Zhou, Junhao Zeng +8
Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In prac…
Project-Level C-to-Rust Translation via Pointer Knowledge Graphs
Zhiqiang Yuan, Wenjun Mao, Zhuo Chen +4
Translating C code into safe Rust is an effective way to ensure memory safety. Compared to rule-based approaches, which often produce largely unsafe Rust code, LLM-based methods ge…
TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment
Zhiqiang Yuan, Weitong Chen, Hanlin Wang +3
Code translation transforms code between programming languages while preserving functionality, which is critical in software development and maintenance. While traditional learning…
No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation
Zhiqiang Yuan, Yiling Lou, Mingwei Liu +4
Unit testing is essential in detecting bugs in functionally-discrete program units. Manually writing high-quality unit tests is time-consuming and laborious. Although traditional t…
SE Factual Knowledge in Frozen Giant Code Model: A Study on FQN and its Retrieval
Qing Huang, Dianshu Liao, Zhenchang Xing +4
Pre-trained giant code models (PCMs) start coming into the developers' daily practices. Understanding what types of and how much software knowledge is packed into PCMs is the found…
Prompt-tuned Code Language Model as a Neural Knowledge Base for Type Inference in Statically-Typed Partial Code
Qing Huang, Zhiqiang Yuan, Zhenchang Xing +3
Partial code usually involves non-fully-qualified type names (non-FQNs) and undeclared receiving objects. Resolving the FQNs of these non-FQN types and undeclared receiving objects…
1+1>2: Programming Know-What and Know-How Knowledge Fusion, Semantic Enrichment and Coherent Application
Qing Huang, Zhiqiang Yuan, Zhenchang Xing +3
Software programming requires both API reference (know-what) knowledge and programming task (know-how) knowledge. Lots of programming know-what and know-how knowledge is documented…