Jieke Shi
YOU?
Author Swipe
View article: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework Open
Current learning-based Automated Vulnerability Repair (AVR) approaches, while promising, often fail to generalize effectively in real-world scenarios. Our diagnostic analysis reveals three fundamental weaknesses in state-of-the-art AVR app…
View article: Curiosity-Driven Testing for Sequential Decision-Making Process
Curiosity-Driven Testing for Sequential Decision-Making Process Open
Sequential decision-making processes (SDPs) are fundamental for complex real-world challenges, such as autonomous driving, robotic control, and traffic management. While recent advances in Deep Learning (DL) have led to mature solutions fo…
View article: "My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants
"My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants Open
This paper aims to explore fundamental questions in the era when AI coding assistants like GitHub Copilot are widely adopted: what do developers truly value and criticize in AI coding assistants, and what does this reveal about their needs…
View article: Mut4All: Fuzzing Compilers via LLM-Synthesized Mutators Learned from Bug Reports
Mut4All: Fuzzing Compilers via LLM-Synthesized Mutators Learned from Bug Reports Open
Mutation-based fuzzing is effective for uncovering compiler bugs, but designing high-quality mutators for modern languages with complex constructs (e.g., templates, macros) remains challenging. Existing methods rely heavily on manual desig…
View article: SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents
SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents Open
Static program slicing, which extracts the executable portions of a program that affect the values at a specific location, supports many software analysis tasks such as debugging and security auditing. However, traditional slicing tools re…
View article: Back to the Basics: Rethinking Issue-Commit Linking with LLM-Assisted Retrieval
Back to the Basics: Rethinking Issue-Commit Linking with LLM-Assisted Retrieval Open
Issue-commit linking, which connects issues with commits that fix them, is crucial for software maintenance. Existing approaches have shown promise in automatically recovering these links. Evaluations of these techniques assess their abili…
View article: Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning
Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning Open
Large Language Models (LLMs) have significantly advanced automated code generation, yet they struggle with complex coding tasks requiring multi-step logical reasoning. High-quality reasoning data is crucial for improving LLMs' reasoning ca…
View article: From Code to Courtroom: LLMs as the New Software Judges
From Code to Courtroom: LLMs as the New Software Judges Open
Recently, Large Language Models (LLMs) have been increasingly used to automate SE tasks such as code generation and summarization. However, evaluating the quality of LLM-generated software artifacts remains challenging. Human evaluation, w…
View article: ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models Open
CodeLLMs have demonstrated remarkable advancements in software engineering tasks. However, while these models can generate functionally correct code, they often produce code that is inefficient in terms of runtime. This inefficiency is par…
View article: Prioritizing Speech Test Cases
Prioritizing Speech Test Cases Open
As Automated Speech Recognition (ASR) systems gain widespread acceptance, there is a pressing need to rigorously test and enhance their performance. Nonetheless, the process of collecting and executing speech test cases is typically both c…
View article: Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs
Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs Open
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 testing control systems is falsification, which aims to fin…
View article: Ecosystem of Large Language Models for Code
Ecosystem of Large Language Models for Code Open
The availability of vast amounts of publicly accessible data of source code and the advances in modern language models, coupled with increasing computational resources, have led to a remarkable surge in the development of large language mo…
View article: Greening Large Language Models of Code
Greening Large Language Models of Code Open
Large language models of code have shown remarkable effectiveness across various software engineering tasks. Despite the availability of many cloud services built upon these powerful models, there remain several scenarios where developers …
View article: Curiosity-Driven Testing for Sequential Decision-Making Process
Curiosity-Driven Testing for Sequential Decision-Making Process Open
Sequential decision-making processes (SDPs) are fundamental for complex real-world challenges, such as autonomous driving, robotic control, and traffic management. While recent advances in Deep Learning (DL) have led to mature solutions fo…
View article: Unveiling Memorization in Code Models
Unveiling Memorization in Code Models Open
The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of lin…
View article: Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead
Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead Open
Large Language Models (LLMs) have recently shown remarkable capabilities in various software engineering tasks, spurring the rapid growth of the Large Language Models for Software Engineering (LLM4SE) area. However, limited attention has b…
View article: Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models
Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models Open
Given large-scale source code datasets available in open-source projects and advanced large language models, recent code models have been proposed to address a series of critical software engineering tasks, such as program repair and code …
View article: Greening Large Language Models of Code
Greening Large Language Models of Code Open
Large language models of code have shown remarkable effectiveness across various software engineering tasks. Despite the availability of many cloud services built upon these powerful models, there remain several scenarios where developers …
View article: Unveiling Memorization in Code Models
Unveiling Memorization in Code Models Open
The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of lin…
View article: What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issues
What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issues Open
Artificial Intelligence systems, which benefit from the availability of large-scale datasets and increasing computational power, have become effective solutions to various critical tasks, such as natural language understanding, speech reco…
View article: Prioritizing Speech Test Cases
Prioritizing Speech Test Cases Open
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 cases is usually expensive and time-consuming, motivating us …
View article: Stealthy Backdoor Attack for Code Models
Stealthy Backdoor Attack for Code Models Open
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 recently, code models were revealed to be vulnerable to backd…
View article: Answer Summarization for Technical Queries: Benchmark and New Approach
Answer Summarization for Technical Queries: Benchmark and New Approach Open
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 existing approaches are assessed solely through user studies. H…
View article: Compressing Pre-trained Models of Code into 3 MB
Compressing Pre-trained Models of Code into 3 MB Open
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 powerful models in software developers' daily workflow: the…
View article: BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets Open
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 paradigm because it saves the interactions with environmen…
View article: Answer Summarization for Technical Queries: Benchmark and New Approach
Answer Summarization for Technical Queries: Benchmark and New Approach Open
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 existing approaches are assessed solely through user studies. T…
View article: Compressing Pre-trained Models of Code into 3 MB
Compressing Pre-trained Models of Code into 3 MB Open
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 powerful models in software developers' daily workflow: the…
View article: Natural attack for pre-trained models of code
Natural attack for pre-trained models of code Open
Pre-trained models of code have achieved success in many important software\nengineering tasks. However, these powerful models are vulnerable to adversarial\nattacks that slightly perturb model inputs to make a victim model produce wrong\n…
View article: Can Identifier Splitting Improve Open-Vocabulary Language Model of Code?
Can Identifier Splitting Improve Open-Vocabulary Language Model of Code? Open
Statistical language models on source code have successfully assisted software engineering tasks. However, developers can create or pick arbitrary identifiers when writing source code. Freely chosen identifiers lead to the notorious out-of…
View article: Can Identifier Splitting Improve Open-Vocabulary Language Model of Code?
Can Identifier Splitting Improve Open-Vocabulary Language Model of Code? Open
Statistical language models on source code have successfully assisted software engineering tasks. However, developers can create or pick arbitrary identifiers when writing source code. Freely chosen identifiers lead to the notorious out-of…