Qihao Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Qihao Zhu has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Junjie Chen
Tianjin University, Tianjin, China
3 shared publications - Lu Zhang
Key Lab of HCST (PKU), MOE; SCS, Peking University, China
3 shared publications - Dan Hao
Key Lab of HCST (PKU), MOE; School of Computer Science, Peking University, China
2 shared publications - Lingming Zhang
University of Illinois at Urbana-Champaign, Champaign, USA
2 shared publications - Wenjie Zhang
National University of Singapore, Singapore, Singapore
2 shared publications - Yakun Zhang
Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China
2 shared publications
Latest Publications
- Open Access
- 4 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 34 (8) , 1-41
LEAM++: Learning for Selective Mutation Fault Construction
Mutation faults are the core of mutation testing and have been widely used in many software testing tasks. Hence, efficiently constructing high-quality mutation faults is critical. To address the effectiveness limitations of traditional and deep learning-based mutation techniques, we first proposed LEAM , utilizing a syntax-guided encoder–decoder architecture with extended grammar rules. While LEAM significantly enhances the effectiveness, it does not consider the associated testing cost. To further improve the efficiency of LEAM , we propose LEAM++ , adopting a novel selective mutation fault construction module based on the probability of grammar rule sequences and the similarity of mutation faults. We extensively evaluate LEAM++ using Defects4J. Regarding effectiveness, the results demonstrate that the mutation faults constructed by LEAM++ can better represent real faults than two traditional techniques ( Major and PIT ) and the deep learning-based technique ( DeepMutation ), and substantially boost three downstream applications, i.e., mutation-based test case prioritization, mutation-based fault localization, and mutation-based bug detection. Regarding efficiency, LEAM++ demonstrates superiority over the four selective mutation testing techniques across three scenarios, i.e., mutation testing, mutation-based test case prioritization, and mutation-based fault localization. Our work serves as an important step toward the efficiently automated construction of mutation faults.
- 4 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 34 (8) , 1-41
Open AccessLEAM++: Learning for Selective Mutation Fault Construction
Mutation faults are the core of mutation testing and have been widely used in many software testing tasks. Hence, efficiently constructing high-quality mutation faults is critical. To address the effectiveness limitations of traditional and deep learning-based mutation techniques, we first proposed LEAM , utilizing a syntax-guided encoder–decoder architecture with extended grammar rules. While LEAM significantly enhances the effectiveness, it does not consider the associated testing cost. To further improve the efficiency of LEAM , we propose LEAM++ , adopting a novel selective mutation fault construction module based on the probability of grammar rule sequences and the similarity of mutation faults. We extensively evaluate LEAM++ using Defects4J. Regarding effectiveness, the results demonstrate that the mutation faults constructed by LEAM++ can better represent real faults than two traditional techniques ( Major and PIT ) and the deep learning-based technique ( DeepMutation ), and substantially boost three downstream applications, i.e., mutation-based test case prioritization, mutation-based fault localization, and mutation-based bug detection. Regarding efficiency, LEAM++ demonstrates superiority over the four selective mutation testing techniques across three scenarios, i.e., mutation testing, mutation-based test case prioritization, and mutation-based fault localization. Our work serves as an important step toward the efficiently automated construction of mutation faults.
- 25 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 51 (9) , 2583-2600
Directional Diffusion-Style Code Editing Pre-Training
Code pre-trained models have shown promising effectiveness in various software engineering tasks. Among these tasks, many tasks are related to software evolution and/or code editing. However, existing code pre-trained models often overlook the real-world code editing data and the evolutionary nature of the editing process. In this paper, to simulate the step-by-step code editing process of human developers, we propose DivoT5, a pre-trained model based on directional diffusion at the data level. In DivoT5, we adopt two categories of pre-training tasks. The first category is mask and denoising tasks augmented with a diffusion direction representing code evolution. That is, we first apply a noising process to the code snippets before evolution, and then ask the pre-training process to restore the snippets with noise into the code snippets after evolution. The second category is tasks aiming to reinforce the evolutionary direction. That is, we first generate various intermediate versions for each pair of snippets before and after evolution, and then ask the pre-training process to transform the intermediate versions into the snippet after evolution for each pair. We evaluate DivoT5 for two code-editing scenarios (including a number of tasks) and one non-editing scenario using four downstream tasks. For each downstream task, we fine-tune the pre-trained DivoT5 on multiple corresponding datasets and evaluate its effectiveness across diverse scenarios Our experimental results show that ivoT5 achieves state-of-the-art (SOTA) performance on most tasks in comparison to models of the same scale (220M), large-scale (770M, 6.7B) models in fine-tuning, and billion-scale (6.7B, 8B, ChatGPT) instruct models in few-shot settings. For one code-editing task (i.e., CodeReview in NL-based CodeRefinement task), DivoT5 pre-trained on top of CodeT5-small (60M) can even outperform CodeT5-base (220M) and other pre-trained models with 220M parameters except for DivoT5 pre-trained on top of CodeT5-base (220M).
- 25 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 51 (9) , 2583-2600
Directional Diffusion-Style Code Editing Pre-Training
Code pre-trained models have shown promising effectiveness in various software engineering tasks. Among these tasks, many tasks are related to software evolution and/or code editing. However, existing code pre-trained models often overlook the real-world code editing data and the evolutionary nature of the editing process. In this paper, to simulate the step-by-step code editing process of human developers, we propose DivoT5, a pre-trained model based on directional diffusion at the data level. In DivoT5, we adopt two categories of pre-training tasks. The first category is mask and denoising tasks augmented with a diffusion direction representing code evolution. That is, we first apply a noising process to the code snippets before evolution, and then ask the pre-training process to restore the snippets with noise into the code snippets after evolution. The second category is tasks aiming to reinforce the evolutionary direction. That is, we first generate various intermediate versions for each pair of snippets before and after evolution, and then ask the pre-training process to transform the intermediate versions into the snippet after evolution for each pair. We evaluate DivoT5 for two code-editing scenarios (including a number of tasks) and one non-editing scenario using four downstream tasks. For each downstream task, we fine-tune the pre-trained DivoT5 on multiple corresponding datasets and evaluate its effectiveness across diverse scenarios Our experimental results show that ivoT5 achieves state-of-the-art (SOTA) performance on most tasks in comparison to models of the same scale (220M), large-scale (770M, 6.7B) models in fine-tuning, and billion-scale (6.7B, 8B, ChatGPT) instruct models in few-shot settings. For one code-editing task (i.e., CodeReview in NL-based CodeRefinement task), DivoT5 pre-trained on top of CodeT5-small (60M) can even outperform CodeT5-base (220M) and other pre-trained models with 220M parameters except for DivoT5 pre-trained on top of CodeT5-base (220M).
- Top Cited PapersOpen Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1607-1619
On the Evaluation of Large Language Models in Unit Test Generation
Unit testing is an essential activity in software development for verifying the correctness of software components. However, manually writing unit tests is challenging and time-consuming. The emergence of Large Language Models (LLMs) offers a new direction for automating unit test generation. Existing research primarily focuses on closed-source LLMs (e.g., ChatGPT and CodeX) with fixed prompting strategies, leaving the capabilities of advanced open-source LLMs with various prompting settings unexplored. Particularly, open-source LLMs offer advantages in data privacy protection and have demonstrated superior performance in some tasks. Moreover, effective prompting is crucial for maximizing LLMs' capabilities. In this paper, we conduct the first empirical study to fill this gap, based on 17 Java projects, five widely-used open-source LLMs with different structures and parameter sizes, and comprehensive evaluation metrics. Our findings highlight the significant influence of various prompt factors, show the performance of open-source LLMs compared to the commercial GPT-4 and the traditional Evosuite, and identify limitations in LLM-based unit test generation. We then derive a series of implications from our study to guide future research and practical use of LLM-based unit test generation.
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1607-1619
Top Cited PapersOpen AccessOn the Evaluation of Large Language Models in Unit Test Generation
Unit testing is an essential activity in software development for verifying the correctness of software components. However, manually writing unit tests is challenging and time-consuming. The emergence of Large Language Models (LLMs) offers a new direction for automating unit test generation. Existing research primarily focuses on closed-source LLMs (e.g., ChatGPT and CodeX) with fixed prompting strategies, leaving the capabilities of advanced open-source LLMs with various prompting settings unexplored. Particularly, open-source LLMs offer advantages in data privacy protection and have demonstrated superior performance in some tasks. Moreover, effective prompting is crucial for maximizing LLMs' capabilities. In this paper, we conduct the first empirical study to fill this gap, based on 17 Java projects, five widely-used open-source LLMs with different structures and parameter sizes, and comprehensive evaluation metrics. Our findings highlight the significant influence of various prompt factors, show the performance of open-source LLMs compared to the commercial GPT-4 and the traditional Evosuite, and identify limitations in LLM-based unit test generation. We then derive a series of implications from our study to guide future research and practical use of LLM-based unit test generation.
- Open Access
- 11 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 869-881
Synthesis-Based Enhancement for GUI Test Case Migration
GUI test case migration is the process of migrating GUI test cases from a source app to a target app for a specific functionality. However, test cases obtained via existing migration approaches can hardly be directly used to test target functionalities and typically require additional manual modifications. This problem may significantly impact the effectiveness of testing target functionalities and the practical applicability of migration approaches. In this paper, we propose MigratePro, the first approach to enhancing GUI test case migration via synthesizing a new test case based on multiple test cases for the same functionality migrated from various source apps to the target app. The aim of MigratePro is to produce functional test cases with less human intervention. Specifically, given multiple migrated test cases for the same functionality in the target app, MigratePro first combines all the GUI states related to these migrated test cases into an overall state-sequence. Then, MigratePro organizes events and assertions from migrated test cases according to the overall state-sequence and endeavors to remove the should-be-removed events and assertions, while also incorporating some connection events in order to make the should-be-included events and assertions executable. Our evaluation on 30 apps, 34 functionalities, and 127 test cases shows that MigratePro improves the capability of three representative migration approaches (i.e., Craftdroid, AppFlow, ATM), successfully improving testing the target functionalities by 86%, 333%, and 300%, respectively. These results underscore the generalizability of MigratePro for effectively enhancing migration approaches.
- 11 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 869-881
Open AccessSynthesis-Based Enhancement for GUI Test Case Migration
GUI test case migration is the process of migrating GUI test cases from a source app to a target app for a specific functionality. However, test cases obtained via existing migration approaches can hardly be directly used to test target functionalities and typically require additional manual modifications. This problem may significantly impact the effectiveness of testing target functionalities and the practical applicability of migration approaches. In this paper, we propose MigratePro, the first approach to enhancing GUI test case migration via synthesizing a new test case based on multiple test cases for the same functionality migrated from various source apps to the target app. The aim of MigratePro is to produce functional test cases with less human intervention. Specifically, given multiple migrated test cases for the same functionality in the target app, MigratePro first combines all the GUI states related to these migrated test cases into an overall state-sequence. Then, MigratePro organizes events and assertions from migrated test cases according to the overall state-sequence and endeavors to remove the should-be-removed events and assertions, while also incorporating some connection events in order to make the should-be-included events and assertions executable. Our evaluation on 30 apps, 34 functionalities, and 127 test cases shows that MigratePro improves the capability of three representative migration approaches (i.e., Craftdroid, AppFlow, ATM), successfully improving testing the target functionalities by 86%, 333%, and 300%, respectively. These results underscore the generalizability of MigratePro for effectively enhancing migration approaches.
- Open Access
- 20 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 61-63
The ET Program Repair Tool for Java
This is the ET tool participating in APR-Comp 2024. It is an end-to-end program repair approach that performs fault localization, patch generation, and patch validation. ET is ranked as #1 in the Functional Errors - Java track.
- 20 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 61-63
Open AccessThe ET Program Repair Tool for Java
This is the ET tool participating in APR-Comp 2024. It is an end-to-end program repair approach that performs fault localization, patch generation, and patch validation. ET is ranked as #1 in the Functional Errors - Java track.
- Open Access
- 6 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Learning-based Widget Matching for Migrating GUI Test Cases
GUI test case migration is to migrate GUI test cases from a source app to a target app. The key of test case migration is widget matching. Recently, researchers have proposed various approaches by formulating widget matching as a matching task. However, since these matching approaches depend on static word embeddings without using contextual information to represent widgets and manually formulated matching functions, there are main limitations of these matching approaches when handling complex matching relations in apps. To address the limitations, we propose the first learning-based widget matching approach named TEMdroid (TEst Migration) for test case migration. Unlike the existing approaches, TEMdroid uses BERT to capture contextual information and learns a matching model to match widgets. Additionally, to balance the significant imbalance between positive and negative samples in apps, we design a two-stage training strategy where we first train a hard-negative sample miner to mine hard-negative samples, and further train a matching model using positive samples and mined hard-negative samples. Our evaluation on 34 apps shows that TEM-droid is effective in event matching (i.e., widget matching and target event synthesis) and test case migration. For event matching, TEM-droid's Top1 accuracy is 76%, improving over 17% compared to baselines. For test case migration, TEMdroid's F1 score is 89%, also 7% improvement compared to the baseline approach.
- 6 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessLearning-based Widget Matching for Migrating GUI Test Cases
GUI test case migration is to migrate GUI test cases from a source app to a target app. The key of test case migration is widget matching. Recently, researchers have proposed various approaches by formulating widget matching as a matching task. However, since these matching approaches depend on static word embeddings without using contextual information to represent widgets and manually formulated matching functions, there are main limitations of these matching approaches when handling complex matching relations in apps. To address the limitations, we propose the first learning-based widget matching approach named TEMdroid (TEst Migration) for test case migration. Unlike the existing approaches, TEMdroid uses BERT to capture contextual information and learns a matching model to match widgets. Additionally, to balance the significant imbalance between positive and negative samples in apps, we design a two-stage training strategy where we first train a hard-negative sample miner to mine hard-negative samples, and further train a matching model using positive samples and mined hard-negative samples. Our evaluation on 34 apps shows that TEM-droid is effective in event matching (i.e., widget matching and target event synthesis) and test case migration. For event matching, TEM-droid's Top1 accuracy is 76%, improving over 17% compared to baselines. For test case migration, TEMdroid's F1 score is 89%, also 7% improvement compared to the baseline approach.
- Open Access
Generative Transformers for Design Concept Generation
Generating novel and useful concepts is essential during the early design stage to explore a large variety of design opportunities, which usually requires advanced design thinking ability and a wide range of knowledge from designers. Growing works on computer-aided tools have explored the retrieval of knowledge and heuristics from design data. However, they only provide stimuli to inspire designers from limited aspects. This study explores the recent advance of the natural language generation (NLG) technique in the artificial intelligence (AI) field to automate the early-stage design concept generation. Specifically, a novel approach utilizing the generative pre-trained transformer (GPT) is proposed to leverage the knowledge and reasoning from textual data and transform them into new concepts in understandable language. Three concept generation tasks are defined to leverage different knowledge and reasoning: domain knowledge synthesis, problem-driven synthesis, and analogy-driven synthesis. The experiments with both human and data-driven evaluation show good performance in generating novel and useful concepts.
Open AccessGenerative Transformers for Design Concept Generation
Generating novel and useful concepts is essential during the early design stage to explore a large variety of design opportunities, which usually requires advanced design thinking ability and a wide range of knowledge from designers. Growing works on computer-aided tools have explored the retrieval of knowledge and heuristics from design data. However, they only provide stimuli to inspire designers from limited aspects. This study explores the recent advance of the natural language generation (NLG) technique in the artificial intelligence (AI) field to automate the early-stage design concept generation. Specifically, a novel approach utilizing the generative pre-trained transformer (GPT) is proposed to leverage the knowledge and reasoning from textual data and transform them into new concepts in understandable language. Three concept generation tasks are defined to leverage different knowledge and reasoning: domain knowledge synthesis, problem-driven synthesis, and analogy-driven synthesis. The experiments with both human and data-driven evaluation show good performance in generating novel and useful concepts.
- Open Access
- 10 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Learning to Construct Better Mutation Faults
Mutation faults are the core of mutation testing and have been widely used in many other software testing and debugging tasks. Hence, constructing high-quality mutation faults is critical. There are many traditional mutation techniques that construct syntactic mutation faults based on a limited set of manually-defined mutation operators. To improve them, the state-of-the-art deep-learning (DL) based technique (i.e., DeepMutation) has been proposed to construct mutation faults by learning from real faults via classic sequence-to-sequence neural machine translation (NMT). However, its performance is not satisfactory since it cannot ensure syntactic correctness of constructed mutation faults and suffers from the effectiveness issue due to the huge search space and limited features by simply treating each targeted method as a token stream. In this work, we propose a novel DL-based mutation technique (i.e., LEAM) to overcome the limitations of both traditional techniques and DeepMutation. LEAM adapts the syntax-guided encoder-decoder architecture by extending a set of grammar rules specific to our mutation task, to guarantee syntactic correctness of constructed mutation faults. Instead of predicting a sequence of tokens one by one to form a whole mutated method, it predicts the statements to be mutated under the context of the targeted method to reduce search space, and then predicts grammar rules for mutation fault construction based on both semantic and structural features in AST. We conducted an extensive study to evaluate LEAM based on the widely-used Defects4J benchmark. The results demonstrate that the mutation faults constructed by LEAM can not only better represent real faults than two state-of-the-art traditional techniques (i.e., Major and PIT) and DeepMutation, but also substantially boost two important downstream applications of mutation faults, i.e., test case prioritization and fault localization.
- 10 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessLearning to Construct Better Mutation Faults
Mutation faults are the core of mutation testing and have been widely used in many other software testing and debugging tasks. Hence, constructing high-quality mutation faults is critical. There are many traditional mutation techniques that construct syntactic mutation faults based on a limited set of manually-defined mutation operators. To improve them, the state-of-the-art deep-learning (DL) based technique (i.e., DeepMutation) has been proposed to construct mutation faults by learning from real faults via classic sequence-to-sequence neural machine translation (NMT). However, its performance is not satisfactory since it cannot ensure syntactic correctness of constructed mutation faults and suffers from the effectiveness issue due to the huge search space and limited features by simply treating each targeted method as a token stream. In this work, we propose a novel DL-based mutation technique (i.e., LEAM) to overcome the limitations of both traditional techniques and DeepMutation. LEAM adapts the syntax-guided encoder-decoder architecture by extending a set of grammar rules specific to our mutation task, to guarantee syntactic correctness of constructed mutation faults. Instead of predicting a sequence of tokens one by one to form a whole mutated method, it predicts the statements to be mutated under the context of the targeted method to reduce search space, and then predicts grammar rules for mutation fault construction based on both semantic and structural features in AST. We conducted an extensive study to evaluate LEAM based on the widely-used Defects4J benchmark. The results demonstrate that the mutation faults constructed by LEAM can not only better represent real faults than two state-of-the-art traditional techniques (i.e., Major and PIT) and DeepMutation, but also substantially boost two important downstream applications of mutation faults, i.e., test case prioritization and fault localization.