Sai Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sai Zhang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Xiaowang Zhang
Tianjin University
5 shared publications - Zhiyong Feng
Tianjin University, Tianjin, China
5 shared publications - Minghui Zou
College of Intelligence and Computing, Tianjin University, Tianjin, China
3 shared publications - Ronghui Guo
College of Intelligence and Computing, Tianjin University, Tianjin, China
3 shared publications - Zhiqiang Zhuang
Tianjin University
2 shared publications - Fangzhou Xu
College of Intelligence and Computing, Tianjin University, Tianjin, China
1 shared publication
Latest Publications
- Open Access
- 3 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 34 (6) , 1-46
Empowering Agile-Based Generative Software Development through Human-AI Teamwork
In software development, the raw requirements proposed by users are frequently incomplete, which impedes the complete implementation of software functionalities. With the emergence of large language models, the exploration of generating software through user requirements has attracted attention. Recent methods with the top-down waterfall model employ a questioning approach for requirement completion, attempting to explore further user requirements. However, users, constrained by their domain knowledge, result in a lack of effective acceptance criteria during the requirement completion, failing to fully capture the implicit needs of the user. Moreover, the cumulative errors of the waterfall model can lead to discrepancies between the generated code and user requirements. The Agile methodologies reduce cumulative errors of the waterfall model through lightweight iteration and collaboration with users, but the challenge lies in ensuring semantic consistency between user requirements and the code generated by the agent. To address these challenges, we propose AgileGen, an agile-based generative software development through human-AI teamwork. Unlike existing questioning agents, AgileGen adopts a novel collaborative approach that breaks free from the constraints of domain knowledge by initiating the end-user perspective to complete the acceptance criteria. By introducing the Gherkin language, AgileGen attempts for the first time to use testable requirement descriptions as a bridge for semantic consistency between requirements and code, aiming to ensure that software products meet actual user requirements by defining user scenarios that include acceptance criteria. Additionally, we innovate in the human-AI teamwork model, allowing users to participate in decision-making processes they do well and significantly enhancing the completeness of software functionality. To ensure semantic consistency between requirements and generated code, we derive consistency factors from Gherkin to drive the subsequent software code generation. Finally, to improve the reliability of user scenarios, we also introduce a memory pool mechanism, collecting user decision-making scenarios and recommending them to new users with similar requirements. AgileGen, as a user-friendly interactive system, significantly outperformed existing best methods by 16.4% and garnered higher user satisfaction.
- 3 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 34 (6) , 1-46
Open AccessEmpowering Agile-Based Generative Software Development through Human-AI Teamwork
In software development, the raw requirements proposed by users are frequently incomplete, which impedes the complete implementation of software functionalities. With the emergence of large language models, the exploration of generating software through user requirements has attracted attention. Recent methods with the top-down waterfall model employ a questioning approach for requirement completion, attempting to explore further user requirements. However, users, constrained by their domain knowledge, result in a lack of effective acceptance criteria during the requirement completion, failing to fully capture the implicit needs of the user. Moreover, the cumulative errors of the waterfall model can lead to discrepancies between the generated code and user requirements. The Agile methodologies reduce cumulative errors of the waterfall model through lightweight iteration and collaboration with users, but the challenge lies in ensuring semantic consistency between user requirements and the code generated by the agent. To address these challenges, we propose AgileGen, an agile-based generative software development through human-AI teamwork. Unlike existing questioning agents, AgileGen adopts a novel collaborative approach that breaks free from the constraints of domain knowledge by initiating the end-user perspective to complete the acceptance criteria. By introducing the Gherkin language, AgileGen attempts for the first time to use testable requirement descriptions as a bridge for semantic consistency between requirements and code, aiming to ensure that software products meet actual user requirements by defining user scenarios that include acceptance criteria. Additionally, we innovate in the human-AI teamwork model, allowing users to participate in decision-making processes they do well and significantly enhancing the completeness of software functionality. To ensure semantic consistency between requirements and generated code, we derive consistency factors from Gherkin to drive the subsequent software code generation. Finally, to improve the reliability of user scenarios, we also introduce a memory pool mechanism, collecting user decision-making scenarios and recommending them to new users with similar requirements. AgileGen, as a user-friendly interactive system, significantly outperformed existing best methods by 16.4% and garnered higher user satisfaction.
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1558-1562
TAT: Improving Stance Detection on Social Media through Thought Alignment with LLMs
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1558-1562
Open AccessTAT: Improving Stance Detection on Social Media through Thought Alignment with LLMs
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 706-716
Graph Local Homophily Network for Anomaly Detection
In graph anomaly detection (GAD), the fact that anomalous nodes usually exhibit high heterophily, while most Graph Neural Networks (GNNs) have homophily assumptions, leads to poor performance. Many studies have attempted to solve this problem by employing a set of graph filters covering various frequencies. Their ultimate goal is to design the most appropriate spectral filter to capture the complex signals generated by normals and anomalies. The critical aspect lies in the fusion of information from filters with different frequency response functions. However, existing methods lack a clear indicator to guide the fusion of information at different frequencies. In this paper, we find that local homophily is a valuable metric for assessing the weights of high- and low-frequency information at the node level, and explicitly point out that the accuracy of local homophily is positively correlated with the accuracy of anomaly detection. Moreover, we unveil the phenomenon of camouflage in anomalous, wherein these nodes disguise themselves by making their features resemble those of surrounding normals. Based on this investigation, we propose the Graph Local Homophily Network for Anomaly Detection (GLHAD). Specifically, we first identify the local homophily of the nodes in the graph under the supervision of the labeled nodes, where two contrasting paradigms are employed to resist the camouflage of anomalies. Then, the local homophily-based combination module combines low- and high-frequency signals based on the predicted local homophily. Eventually, the node representations of different layers are aggregated to make finally predictions.Comprehensive experiments on four anomaly detection datasets show that GLHAD outperforms other state-of-the-art baselines.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 706-716
Open AccessGraph Local Homophily Network for Anomaly Detection
In graph anomaly detection (GAD), the fact that anomalous nodes usually exhibit high heterophily, while most Graph Neural Networks (GNNs) have homophily assumptions, leads to poor performance. Many studies have attempted to solve this problem by employing a set of graph filters covering various frequencies. Their ultimate goal is to design the most appropriate spectral filter to capture the complex signals generated by normals and anomalies. The critical aspect lies in the fusion of information from filters with different frequency response functions. However, existing methods lack a clear indicator to guide the fusion of information at different frequencies. In this paper, we find that local homophily is a valuable metric for assessing the weights of high- and low-frequency information at the node level, and explicitly point out that the accuracy of local homophily is positively correlated with the accuracy of anomaly detection. Moreover, we unveil the phenomenon of camouflage in anomalous, wherein these nodes disguise themselves by making their features resemble those of surrounding normals. Based on this investigation, we propose the Graph Local Homophily Network for Anomaly Detection (GLHAD). Specifically, we first identify the local homophily of the nodes in the graph under the supervision of the labeled nodes, where two contrasting paradigms are employed to resist the camouflage of anomalies. Then, the local homophily-based combination module combines low- and high-frequency signals based on the predicted local homophily. Eventually, the node representations of different layers are aggregated to make finally predictions.Comprehensive experiments on four anomaly detection datasets show that GLHAD outperforms other state-of-the-art baselines.
- 23 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (9) , 11872-11883
Relation-Aware Heterogeneous Graph Network for Learning Intermodal Semantics in Textbook Question Answering
Textbook question answering (TQA) task aims to infer answers for given questions from a multimodal context, including text and diagrams. The existing studies have aggregated intramodal semantics extracted from a single modality but have yet to capture the intermodal semantics between different modalities. A major challenge in learning intermodal semantics is maintaining lossless intramodal semantics while bridging the gap of semantics caused by heterogeneity. In this article, we propose an intermodal relation-aware heterogeneous graph network (IMR-HGN) to extract the intermodal semantics for TQA, which aggregates different modalities while learning features rather than representing them independently. First, we design a multidomain consistent representation (MDCR) to eliminate semantic gaps by capturing intermodal features while maintaining lossless intramodal semantics in multidomains. Furthermore, we present neighbor-based relation inpainting (NRI) to reduce semantic ambiguity via repairing fuzzy relations with correlations of relations. Finally, we propose hierarchical multisemantics aggregation (HMSA) to guarantee the completeness of semantics by aggregating features of nodes and relations with a reconstruction network (RN). Experimental results show that IMR-HGN could extract the intermodal semantics of answers, achieving a 2.16% improvement on the validation set of the TQA dataset and a 3.04% increase on the test set of the AI2D dataset.
- 23 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (9) , 11872-11883
Relation-Aware Heterogeneous Graph Network for Learning Intermodal Semantics in Textbook Question Answering
Textbook question answering (TQA) task aims to infer answers for given questions from a multimodal context, including text and diagrams. The existing studies have aggregated intramodal semantics extracted from a single modality but have yet to capture the intermodal semantics between different modalities. A major challenge in learning intermodal semantics is maintaining lossless intramodal semantics while bridging the gap of semantics caused by heterogeneity. In this article, we propose an intermodal relation-aware heterogeneous graph network (IMR-HGN) to extract the intermodal semantics for TQA, which aggregates different modalities while learning features rather than representing them independently. First, we design a multidomain consistent representation (MDCR) to eliminate semantic gaps by capturing intermodal features while maintaining lossless intramodal semantics in multidomains. Furthermore, we present neighbor-based relation inpainting (NRI) to reduce semantic ambiguity via repairing fuzzy relations with correlations of relations. Finally, we propose hierarchical multisemantics aggregation (HMSA) to guarantee the completeness of semantics by aggregating features of nodes and relations with a reconstruction network (RN). Experimental results show that IMR-HGN could extract the intermodal semantics of answers, achieving a 2.16% improvement on the validation set of the TQA dataset and a 3.04% increase on the test set of the AI2D dataset.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 196-199
Persona Consistent Dialogue Generation via Contrastive Learning
The inclusion of explicit personas in generation models has gained significant attention as a means of developing intelligent dialogue agents. However, large pretrained generation models often produce inconsistent responses with persona. We investigate the model generation behavior to identify signs of inconsistency and observe inconsistent behavior patterns. In this work, we introduce contrastive learning into persona consistent dialogue generation, building on the idea that humans learn not just from positive feedback, but also from identifying and correcting undesirable behaviors. According to the inconsistent patterns, we design two strategies to construct high-quality negative samples, which are critical for contrastive learning efficacy. Experimental results demonstrate that our method can effectively improve the consistency of the responses while improving its dialogue quality on both automatic and human evaluation.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 196-199
Open AccessPersona Consistent Dialogue Generation via Contrastive Learning
The inclusion of explicit personas in generation models has gained significant attention as a means of developing intelligent dialogue agents. However, large pretrained generation models often produce inconsistent responses with persona. We investigate the model generation behavior to identify signs of inconsistency and observe inconsistent behavior patterns. In this work, we introduce contrastive learning into persona consistent dialogue generation, building on the idea that humans learn not just from positive feedback, but also from identifying and correcting undesirable behaviors. According to the inconsistent patterns, we design two strategies to construct high-quality negative samples, which are critical for contrastive learning efficacy. Experimental results demonstrate that our method can effectively improve the consistency of the responses while improving its dialogue quality on both automatic and human evaluation.
- Open Access
- 27 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 55-63
Improving Empathetic Dialogue Generation with Semantics Decoupling
- 27 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 55-63
Open AccessImproving Empathetic Dialogue Generation with Semantics Decoupling