Hongyu Zhang

• Doctor of Philosophy
• Professor (Associate) at University of Newcastle Australia

LLM-based automated program repair methods have attracted significant attention for their state-of-the-art performance. However, they were primarily evaluated on a few well known datasets like Defects4J, raising questions about their effectiveness on new datasets. In this study, we evaluate 11 top-performing LLMs on DEFECTS4J-TRANS, a new dataset d...

Source code summaries are short natural language descriptions of code snippets that help developers better understand and maintain source code. There has been a surge of work on automatic code summarization to reduce the burden of writing summaries manually. However, contemporary approaches only leverage the information within the boundary of the m...

The increasing complexity of modern software systems necessitates robust autonomic self-management capabilities. While Large Language Models (LLMs) demonstrate potential in this domain, they often face challenges in adapting their general knowledge to specific service contexts. To address this limitation, we propose ServiceOdyssey, a self-learning...

Automated Program Repair (APR) has garnered significant attention due to its potential to streamline the bug repair process for human developers. Recently, LLM-based APR methods have shown promise in repairing real-world bugs. However, existing APR methods often utilize patches generated by LLMs without further optimization, resulting in reduced ef...

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pretraining language models on a large-scale code corpus is computationally expensive. Fortunately, many off-the-sh...

Recently, an increasing number of AI-driven programming assistants powered by code LLMs have been integrated into various real-world software development environments, significantly boosting developer productivity. However, existing code generation benchmarks primarily focus on general-purpose scenarios, leaving the code generation performance of L...

Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of such code translators. However, previous benchmarks mostly provide fine-grained samples, focusing at...

Code retrieval, which retrieves code snippets based on users' natural language descriptions, is widely used by developers and plays a pivotal role in real-world software development. The advent of deep learning has shifted the retrieval paradigm from lexical-based matching towards leveraging deep learning models to encode source code and queries in...

Test-to-code traceability links (TCTLs) establish links between test artifacts and code artifacts. These links enable developers and testers to quickly identify the specific pieces of code tested by particular test cases, thus facilitating more efficient debugging, regression testing, and maintenance activities. Various approaches, based on distinc...

To meet the increasing demand for customized software, highly configurable systems become essential in practice. Such systems offer many options to configure, and ensuring the reliability of these systems is critical. A widely-used evaluation metric for testing these systems is \(t\) -wise coverage, where \(t\) represents testing strength, and its...

Code search plays a crucial role in software development, enabling developers to retrieve and reuse code using natural language queries. While the performance of code search models improves with an increase in high-quality data, obtaining such data can be challenging and expensive. Recently, large language models (LLMs) such as ChatGPT have made re...

Code generation aims to automatically generate code snippets that meet given natural language requirements and plays an important role in software development. Although Code LLMs have shown excellent performance in this domain, their long generation time poses a signification limitation in practice use. In this paper, we first conduct an in-depth p...

Just-in-time software defect prediction (JIT-SDP) is a fine-grained, easy-to-trace, and practical method. Unfortunately, JIT-SDP usually suffers from the class imbalance problem, which affects the performance of the models. Data sampling is one of the commonly used class imbalance techniques to overcome this problem. However, there is a lack of com...

Finetuning language models (LMs) is crucial for adapting the models to downstream data and tasks. However, full finetuning is usually costly. Existing work, such as parameter-efficient finetuning (PEFT), often focuses on \textit{how to finetune} but neglects the issue of \textit{where to finetune}. As a pioneering work on answering where to finetun...

Log parsing, the process of converting raw log messages into structured formats, is an important initial step for automated analysis of logs of large-scale software systems. Traditional log parsers often rely on heuristics or handcrafted features, which may not generalize well across diverse log sources or require extensive model tuning. Recently,...

To evaluate the code generation capabilities of Large Language Models (LLMs) in complex real-world software development scenarios, many evaluation approaches have been developed. They typically leverage contextual code from the latest version of a project to facilitate LLMs in accurately generating the desired function. However, such evaluation app...

Reusing APIs can greatly expedite the software development process and reduce programming effort. To learn how to use APIs, developers often rely on API learning resources (such as API references and tutorials) that contain rich and valuable API knowledge. In recent years, numerous API analytic approaches have been presented to help developers mine...

Automated Program Repair (APR) has garnered significant attention due to its potential to streamline the bug repair process for human developers. Recently, LLM-based APR methods have shown promise in repairing real-world bugs. However, existing APR methods often utilize patches generated by LLMs without further optimization, resulting in reduced ef...

The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table, enabling users to gain insights from vast amounts of data. Recently, many deep learning-based approaches have been developed for NL2Vis. Despite the considerable efforts made by these approaches, chal...

Large-scale software-intensive systems often produce a large volume of logs to record runtime status and events for troubleshooting purposes. The rich information in log data enables a variety of system management and diagnosis tasks. Over the years, many approaches have been proposed for automated log analytics. However, these approaches usually d...

Large Language Models (LLMs) have garnered considerable attention owing to their remarkable capabilities, leading to an increasing number of companies offering LLMs as services. Different LLMs achieve different performance at different costs. A challenge for users lies in choosing the LLMs that best fit their needs, balancing cost and performance....

Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and productivity of computer programming. Currently, there is already a thriving research community focusing on code intelligence, with efforts ranging from software engineerin...

In the field of code intelligence, effectively modeling long-range code poses a significant challenge. Existing pre-trained language models (PLMs) such as UniXcoder have achieved remarkable success, but they still face difficulties with long code inputs. This is mainly due to their limited capacity to maintain contextual continuity and memorize the...

Detecting failures and identifying their root causes promptly and accurately is crucial for ensuring the availability of microservice systems. A typical failure troubleshooting pipeline for microservices consists of two phases: anomaly detection and root cause analysis. While various existing works on root cause analysis require accurate anomaly de...

Fault localization (FL) and automated program repair (APR) are two main tasks of automatic software debugging. Compared with traditional methods, deep learning-based approaches have been demonstrated to achieve better performance in FL and APR tasks. However, the existing deep learning-based FL methods ignore the deep semantic features or only cons...

Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i.e., good-practice commits), while the rest do...

API tutorials are crucial resources as they often provide detailed explanations of how to utilize APIs. Typically, an API tutorial is segmented into a number of consecutive fragments.. If a fragment explains API usage, we regard it as a relevant fragment of the API. Recognizing relevant fragments can aid developers in comprehending, learning, and u...

With the widespread success of deep learning technologies, many trained deep neural network (DNN) models are now publicly available. However, directly reusing the public DNN models for new tasks often fails due to mismatching functionality or performance. Inspired by the notion of modularization and composition in software reuse, we investigate the...

Pre-trained models have been shown effective in many code intelligence tasks, such as automatic code summarization and defect prediction. These models are pre-trained on large-scale unlabeled corpus and then fine-tuned in downstream tasks. However, as the inputs to pre-training and downstream tasks are in different forms, it is hard to fully explor...

Recently, machine learning techniques especially deep learning techniques have made substantial progress on some code intelligence tasks such as code summarization, code search, clone detection, etc. How to represent source code to effectively capture the syntactic, structural, and semantic information is a key challenge. Recent studies show that t...

Code summarization aims to generate concise natural language descriptions for a piece of code, which can help developers comprehend the source code. Analysis of current work shows that the extraction of syntactic and semantic features of source code is crucial for generating high-quality summaries. To provide a more comprehensive feature representa...

Software development plays a crucial role in driving innovation and efficiency across modern societies. To meet the demands of this dynamic field, there is a growing need for an effective software development assistant. However, existing large language models represented by ChatGPT suffer from limited accessibility, including training data and mode...

Deep neural network (DNN) models have become increasingly crucial components in intelligent software systems. However, training a DNN model is typically expensive in terms of both time and money. To address this issue, researchers have recently focused on reusing existing DNN models - borrowing the idea of code reuse in software engineering. Howeve...

Gaussian process (GP) based Bayesian optimization (BO) is a powerful method for optimizing black-box functions efficiently. The practical performance and theoretical guarantees associated with this approach depend on having the correct GP hyperparameter values, which are usually unknown in advance and need to be estimated from the observed data. Ho...

Software logs play an essential role in ensuring the reliability and maintainability of large-scale software systems, as they are often the sole source of runtime information. Log parsing, which converts raw log messages into structured data, is an important initial step towards downstream log analytics. In recent studies, ChatGPT, the current cutt...

Automated code generation can be a powerful technique for software development, significantly reducing developers' efforts and time required to create new code by generating it automatically based on requirements. Recently, OpenAI's language model ChatGPT has emerged as a powerful tool for generating human-like responses to a wide range of textual...

Software clone detection identifies similar or identical code snippets. It has been an active research topic that attracts extensive attention over the last two decades. In recent years, machine learning (ML) based detectors, especially deep learning-based ones, have demonstrated impressive capability on clone detection. It seems that this longstan...

Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large computational cost. In this paper, we conduct an extensive experimental study to explore what happens to layer...

Training deep neural network (DNN) models, which has become an important task in today's software development, is often costly in terms of computational resources and time. With the inspiration of software reuse, building DNN models through reusing existing ones has gained increasing attention recently. Prior approaches to DNN model reuse have two...

In cloud systems, incidents are potential threats to customer satisfaction and business revenue. When customers are affected by incidents, they often request customer support service (CSS) from the cloud provider by submitting a support ticket. Many tickets could be duplicate as they are reported in a distributed and uncoordinated manner. Thus, agg...

Logs generated by large-scale software systems provide crucial information for engineers to understand the system status and diagnose problems of the systems. Log parsing, which converts raw log messages into structured data, is the first step to enabling automated log analytics. Existing log parsers extract the common part as log templates using s...

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited...

Previous research on code intelligence usually trains a deep learning model on a fixed dataset in an offline manner. However, in real-world scenarios, new code repositories emerge incessantly, and the carried new knowledge is beneficial for providing up-to-date code intelligence services to developers. In this paper, we aim at the following problem...

Configurable software systems are employed in many important application domains. Understanding the performance of the systems under all configurations is critical to prevent potential performance issues caused by misconfiguration. However, as the number of configurations can be prohibitively large, it is not possible to measure the system performa...

Large-scale software-intensive systems often generate logs for troubleshooting purpose. The system logs are semi-structured text messages that record the internal status of a system at runtime. In this paper, we propose ADR (Anomaly Detection by workflow Relations), which can mine numerical relations from logs and then utilize the discovered relati...

Developers often use learning resources such as API tutorials and Stack Overflow (SO) to learn how to use an unfamiliar API. An API tutorial can be divided into a number of consecutive units that describe the same topic, denoted as tutorial fragments. We consider a tutorial fragment explaining the API usage knowledge as a relevant fragment of the A...

Non-independent and identically distributed (non-IID) data distribution among clients is considered as the key factor that degrades the performance of federated learning (FL). Several approaches to handle non-IID data, such as personalized FL and federated multitask learning (FMTL), are of great interest to research communities. In this work, first...

Context Incident management plays a significant role in online service systems. Incidents should be mitigated as soon as possible in order to achieve high service stability. However, available resources tend to be limited, and thus engineers have to schedule their tasks carefully. Time to Mitigate (TTM) refers to the time an incident requires to re...

Commit messages are natural language descriptions of code changes, which are important for program understanding and maintenance. However, writing commit messages manually is time-consuming and laborious, especially when the code is updated frequently. Various approaches utilizing generation or retrieval techniques have been proposed to automatical...

Code search, which aims at retrieving the most relevant code fragment for a given natural language query, is a common activity in software development practice. Recently, contrastive learning is widely used in code search research, where many data augmentation approaches for source code (e.g., semantic-preserving program transformation) are propose...