43 citations · 160 across the 25 of their papers we have counts for
26 papers
What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects
Bowen Xu, Boyu Chen
Harness search keeps a change to the prompts, reasoning switches, token budgets or parsers around a frozen model if the change raises a score. Such a gain can come from answers the…
Curiosity-Driven Testing for Sequential Decision-Making Process
Junda He, Zhou Yang, Jieke Shi +5
Sequential decision-making processes (SDPs) are fundamental for complex real-world challenges, such as autonomous driving, robotic control, and traffic management. While recent adv…
Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs
Jieke Shi, Zhou Yang, Junda He +4
Given the increasing adoption of modern AI-enabled control systems, ensuring their safety and reliability has become a critical task in software testing. One prevalent approach to…
PTM4Tag+: Tag Recommendation of Stack Overflow Posts with Pre-trained Models
Junda He, Bowen Xu, Zhou Yang +5
Stack Overflow is one of the most influential Software Question & Answer (SQA) websites, hosting millions of programming-related questions and answers. Tags play a critical role in…
APIDocBooster: An Extract-Then-Abstract Framework Leveraging Large Language Models for Augmenting API Documentation
Chengran Yang, Jiakun Liu, Bowen Xu +5
API documentation is often the most trusted resource for programming. Many approaches have been proposed to augment API documentation by summarizing complementary information from…
Multi-LLM Collaboration + Data-Centric Innovation = 2x Better Vulnerability Repair
Xin Zhou, Kisub Kim, Bowen Xu +2
The advances of deep learning (DL) have paved the way for automatic software vulnerability repair approaches, which effectively learn the mapping from the vulnerable code to the fi…
CCBERT: Self-Supervised Code Change Representation Learning
Xin Zhou, Bowen Xu, DongGyun Han +3
Numerous code changes are made by developers in their daily work, and a superior representation of code changes is desired for effective code change analysis. Recently, Hoang et al…
The Devil is in the Tails: How Long-Tailed Code Distributions Impact Large Language Models
Xin Zhou, Kisub Kim, Bowen Xu +3
Learning-based techniques, especially advanced Large Language Models (LLMs) for code, have gained considerable popularity in various software engineering (SE) tasks. However, most…
Greening Large Language Models of Code
Jieke Shi, Zhou Yang, Hong Jin Kang +3
Large language models of code have shown remarkable effectiveness across various software engineering tasks. Despite the availability of many cloud services built upon these powerf…
Are We Ready to Embrace Generative AI for Software Q&A?
Bowen Xu, Thanh-Dat Nguyen, Thanh Le-Cong +8
Stack Overflow, the world's largest software Q&A (SQA) website, is facing a significant traffic drop due to the emergence of generative AI techniques. ChatGPT is banned by Stack Ov…
Multi-Granularity Detector for Vulnerability Fixes
Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang +9
With the increasing reliance on Open Source Software, users are exposed to third-party library vulnerabilities. Software Composition Analysis (SCA) tools have been created to alert…
A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques
Aftab Hussain, Md Rafiqul Islam Rabin, Toufique Ahmed +4
In this work, we study literature in Explainable AI and Safe AI to understand poisoning of neural models of code. In order to do so, we first establish a novel taxonomy for Trojan…
Generation-based Code Review Automation: How Far Are We?
Xin Zhou, Kisub Kim, Bowen Xu +3
Code review is an effective software quality assurance activity; however, it is labor-intensive and time-consuming. Thus, a number of generation-based automatic code review (ACR) a…
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
Aftab Hussain, Md Rafiqul Islam Rabin, Bowen Xu +2
Although deep neural models substantially reduce the overhead of feature engineering, the features readily available in the inputs might significantly impact training cost and the…
Representation Learning for Stack Overflow Posts: How Far are We?
Junda He, Zhou Xin, Bowen Xu +6
The tremendous success of Stack Overflow has accumulated an extensive corpus of software engineering knowledge, thus motivating researchers to propose various solutions for analyzi…
PatchZero: Zero-Shot Automatic Patch Correctness Assessment
Xin Zhou, Bowen Xu, Kisub Kim +5
Automated Program Repair (APR) techniques have shown more and more promising results in fixing real-world bugs. Despite the effectiveness, APR techniques still face an overfitting…
Prioritizing Speech Test Cases
Zhou Yang, Jieke Shi, Muhammad Hilmi Asyrofi +4
With the wide adoption of automated speech recognition (ASR) systems, it is increasingly important to test and improve ASR systems. However, collecting and executing speech test ca…
Stealthy Backdoor Attack for Code Models
Zhou Yang, Bowen Xu, Jie M. Zhang +4
Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most re…
Duplicate Bug Report Detection: How Far Are We?
Ting Zhang, DongGyun Han, Venkatesh Vinayakarao +5
Many Duplicate Bug Report Detection (DBRD) techniques have been proposed in the research literature. The industry uses some other techniques. Unfortunately, there is insufficient c…
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
Chen Gong, Zhou Yang, Yunpeng Bai +8
Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL…
Answer Summarization for Technical Queries: Benchmark and New Approach
Yang Chengran, Bowen Xu, Ferdian Thung +8
Prior studies have demonstrated that approaches to generate an answer summary for a given technical query in Software Question and Answer (SQA) sites are desired. We find that exis…
Compressing Pre-trained Models of Code into 3 MB
Jieke Shi, Zhou Yang, Bowen Xu +2
Although large pre-trained models of code have delivered significant advancements in various code processing tasks, there is an impediment to the wide and fluent adoption of these…
PTM4Tag: Sharpening Tag Recommendation of Stack Overflow Posts with Pre-trained Models
Junda He, Bowen Xu, Zhou Yang +3
Stack Overflow is often viewed as the most influential Software Question Answer (SQA) website with millions of programming-related questions and answers. Tags play a critical role…
Aspect-Based API Review Classification: How Far Can Pre-Trained Transformer Model Go?
chengran Yang, Bowen Xu, Junaed younus Khan +4
APIs (Application Programming Interfaces) are reusable software libraries and are building blocks for modern rapid software development. Previous research shows that programmers fr…