Jingjing Wang 王晶晶

Associate Professor, Natural Language Processing Lab, Soochow University

Email: djingwang@suda.edu.cn

Address: No.1, Shizi Street, Suzhou, China, 215006

I am an Associate Professor at School of Computer Science and Technology, Soochow University. I am also a Senior Technical Consultant (Part-time) at Microsoft (Asia), China. My research interests focus on Multimodal Computing (especially for Multimodal Information Extraction, Visual-Language Understanding and Generation, Embodied Intelligence), Affective Computing, Large Language Models and AI for Medical Diagnosis. I received my Ph.D. degree from Soochow University in 2019, fortunately advised by Prof. Guodong Zhou and Prof. Shoushan Li. During my career, I am also working with Prof. Min Zhang for advancing Natural Language Processing and Artificial Intelligence technology to benefit humanity.

王晶晶，苏州大学副教授，微软访问学者，苏州大学自然语言处理（NLP）实验室博士，兼任微软（亚洲）工程院高级技术顾问， 主要致力于人工智能（AI）领域中Multimodal Computing (especially for Multimodal Information Extraction, Visual-Language Understanding and Generation, Embodied Intelligence), Affective Computing, Large Language Models and AI for Medical Diagnosis等方向的研究。 截止目前，已在CCF-A类顶会和顶刊，例如ACL、AAAI、WWW、MM、IJCAI、SCIS等发表AI与NLP相关论文数十篇，并主持与参与国家项目多项，拥有多项授权专利。 此外担任AI、NLP领域国际顶级会议ACL、AAAI、WWW、MM、IJCAI等的Area Chair、PC，CCCF期刊编委以及TASLP、TAFFC、SCIS、中国科学、软件学报等国内外重要学术期刊审稿人。 目前合作的企业包括：Microsoft、阿里达摩院、蚂蚁金服等，也乐于推荐本组的学生到上述企业交流、实习与工作。人生寄语：“知者行之始，行者知之成”。

I am actively seeking highly-motivated students to join my research team. Perspective candidates are welcome to email me with your CV or research interests for detailed consultation. Regarding recommendation letters, please be advised that I would like to provide substantive evaluations for candidates with whom I have already had a meaningful collaboration. This would allow me to objectively assess your research competencies, scholarly contributions, and professional development through sustained engagement.

Updates & News

  • [June 21, 2024] 🐂 My four students (Yu Tan, Jianing, Yiding & Jipeng) achieve the Outstanding Graduating Postgraduate.
  • [June 01, 2025] 🔥 Our paper "Boosting LLM's.." is accepted by TASLP 2025 (Top Journal, JCR Q1).
  • [May 15, 2025] 🔥 "Table-Critic: A Multi-Agent Framework.." is accepted by ACL 2025 main conference (CCF A).
  • [Jan. 21, 2025] 🚀 Two papers ("Sherlock" & "Omni-SILA") are accepted by WWW 2025 (CCF A).
  • [Dec. 28, 2024] 🐂 Two students (Yu Tan & Jianing Zhao) in my team achieve the National Scholarship.
  • [Dec. 10, 2024] 🔥 "SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing" is accepted by AAAI 2025 (CCF A).
  • [Dec. 01, 2024] 🔥 "TACL: A Trusted Action-enhanced Curriculum Learning Approach" is accepted by Neurocomputing (Top Journal, JCR Q1).
  • [Jul. 16, 2024] 🚀 Two papers ("Emotion-enriched Text-to-Motion Generation" & "Hawkeye") are accepted by ACM MM 2024 (CCF A).
  • [Feb. 20, 2024] 🚀 Three papers ("ChatASU" etc.) are accepted by COLING 2024 (CCF B).

    • Selected Research

    Multi-Agent System for Structured Information Extraction and Generation

    This research focuses on advancing Text-to-SQL parsing by addressing the critical challenge of semantic accuracy in LLM-generated SQL queries. While fine-tuned large language models excel at producing syntactically valid SQL, they often struggle with semantic consistency, leading to unreliable results in real-world applications.

    To tackle this issue, we introduce SQLFixAgent (Cen et al., AAAI'2025), a novel multi-agent collaborative framework designed to detect and repair erroneous SQL queries. SQLFixAgent integrates three specialized agents: 1) SQLReviewer: Identifies semantic mismatches using rubber duck debugging principles. 2) QueryCrafter: Generates diverse candidate SQL repairs by perturbing user queries. 3) SQLRefiner: Selects the optimal repair through retrieval-augmented reflection and failure memory.

    This framework achieves a 3% improvement in execution accuracy on the challenging BIRD benchmark while maintaining high token efficiency, making it practical for deployment. Beyond this, we investigate robust Text-to-SQL parsing across diverse scenarios, including domain knowledge integration (Spider-DK) and synonym robustness (Spider-Syn). Our work also explores the synergy between fine-tuned and foundation LLMs, demonstrating how agent collaboration can compensate for individual model limitations. In addition, we propose Table-Critic (Yu et al., ACL'2025), a novel multi-agent framework designed to enhance structured table reasoning through collaborative error detection and refinement. While large language models (LLMs) excel in many reasoning tasks, they often struggle with maintaining consistency in multi-step table-based reasoning, leading to cascading errors. Table-Critic demonstrates how structured collaboration among LLM-based agents can overcome inherent limitations in complex reasoning tasks, offering a scalable and interpretable approach for real-world applications in data analysis and decision support.

    Papers: [Cen et al., AAAI'2025] [Code] [PDF], [Yu et al., ACL'2025] [Code] [PDF]

    Multimodal Foundation Model for Video Understanding and Grounding

    The goal is to establish a unified framework for video anomaly detection, advancing precision in identifying and localizing abnormal events across dynamic scenes while enabling interpretable analysis of complex visual patterns.

    Starting from real-world applications in surveillance and social media analysis, we introduce Hawkeye (Zhao et al., ACM MM'24) , the first scene-enhanced video-language model designed for anomaly detection. Hawkeye integrates multimodal context (visual-textual-temporal cues) to recognize subtle anomalies and pinpoint their temporal boundaries in untrimmed videos, This work lays a critical foundation for event typing and spatiotemporal localization in short video understanding.

    Building on this, we investigate low-resource scenarios where annotated anomaly data is scarce. Our Continuous Attention Modeling method (Zhang et al., JOS'23) enhances adaptability by capturing long-range dependencies in sparse anomaly signals. Further, we extend Hawkeye with self-supervised learning to uncover latent patterns across unlabeled videos, improving generalization to unseen anomaly types. To scale solutions, we construct a benchmark suite combining large-scale anomaly annotations and instruction-tuned datasets. This addresses the challenge of diverse event types (e.g., accidents, unusual behaviors) and supports downstream tasks like explainable reasoning.

    Papers: [Zhang et al., JOS'23], [Zhao et al., ACM MM'24 ] [Code] [PDF]

    Publications

    2025

    1. Peiying Yu, Guoxing Chen, Jingjing Wang. Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL, Main Conference), 2025. (CCF A, Corresponding Author)

    2. Jipeng Cen, Jiaxin Liu, Zhixu Li, Jingjing Wang. SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF A, Corresponding Author)

    3. Junxiao Ma, Jingjing Wang, Jiamin Luo, Peiying Yu, Guodong Zhou. Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM. In Proceedings of the Web Conference (WWW), 2025. (CCF A, Corresponding Author)

    4. Jipeng Cen, Jiaxin Liu, Zhixu Li, Jingjing Wang. CPO-SQL: Boosting Small LLMs for Text-to-SQL via Efficient In-Context Learning and Preference Optimization. In Proceedings of the International Conference on Natural Language Processing and Chinese Computing (NLPCC), 2025. (CCF C, Corresponding Author)

    5. Jiamin Luo, Jingjing Wang, Junxiao Ma, Yujie Jin, Shoushan Li, Guodong Zhou. Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos. In Proceedings of the Web Conference (WWW), 2025. (CCF A, Corresponding Author)

    6. Luo Jiamin, Jingjing Wang, Zhou Guodong Multi-modal Reliability-aware Affective Computing. Ruan Jian Xue Bao/Journal of Software (JOS), 2025, 36(2):537-553. (CCF A in Chinese Journal, EI, Corresponding Author)

    7. Tan Yu, Jingjing Wang, Jiamin Luo, Jiawen Wang, Guodong Zhou. TACL: A Trusted Action-enhanced Curriculum Learning Approach to Multimodal Affective Computing. Neurocomputing, 2025, 620:129195. (SCI, JCR Q1, Corresponding Author)

    2024

    1. Jianing Zhao, Jingjing Wang, Yujie Jin, Jiamin Luo, Guodong Zhou. Hawkeye: Discovering and Grounding Implicit Anomalous Sentiment in Recon-videos via Scene-enhanced Video Large Language Model. In Proceedings of the ACM International Conference on Multimedia (ACM MM), 2024, 592-601. (CCF A, Corresponding Author)

    2. Tan Yu, Jingjing Wang, Jiawen Wang, Jiamin Luo, Guodong Zhou. Towards Emotion-enriched Text-to-Motion Generation via LLM-guided Limb-level Emotion Manipulating. In Proceedings of the ACM International Conference on Multimedia (ACM MM), 2024, 612-621. (CCF A, Corresponding Author)

    3. Han Zhang, Jingjing Wang, Jiamin Luo, Guodong Zhou. Continual Attention Modeling for Sucessive Sentiment Analysis in Low resource Scenarios. Ruan Jian Xue Bao/Journal of Software (JOS), 2024, 35(12):5470-5486. (CCF A in Chinese Journal, EI, Corresponding Author)

    4. Yiding Liu, Jingjing Wang, Jiamin Luo, Tao Zeng, Guodong Zhou. ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues. In Proceedings of the International Conference on Computational Linguistics (COLING), 2024, 3075-3085. (CCF B, Corresponding Author)

    5. Jiamin Luo, Jianing Zhao, Jingjing Wang, Guodong Zhou. How to Understand 'Support'? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding. In Proceedings of the International Conference on Computational Linguistics (COLING), 2024. (CCF B, Corresponding Author)

    6. Jiamin Luo, Jingjing Wang, Guodong Zhou. TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection. In Proceedings of the International Conference on Computational Linguistics (COLING), 2024. (CCF B, Corresponding Author)

    7. Jiamin Luo, Jingjing Wang, Guodong Zhou. Topic-Enriched Variational Transformer for Conversational Emotion Detection. In Proceedings of the International Conference on Natural Language Processing and Chinese Computing (NLPCC), 2024, 3-15. (CCF C, Corresponding Author)

    2023

    1. Yiding Liu, Jingjing Wang, Jiamin Luo, Guodong Zhou. LLM-Grounded Conversation Aspect Sentiment Understanding via Muti-Agent Consistency Reflection. Ruan Jian Xue Bao/Journal of Software (JOS), 2023. (CCF A in Chinese Journal, EI, Corresponding Author)

    2. Jianing Zhao, Jingjing Wang, Jiamin Luo, Guodong Zhou. Implicit-enhanced Causal Modeling for Phrasal Visual Grounding. Ruan Jian Xue Bao/Journal of Software (JOS), 2023. (CCF A in Chinese Journal, Corresponding Author)

    3. Jingjing Wang, Jiamin Luo, Guodong Zhou. Fine-Grained Question-Answer Matching via Sentence-Aware Contrastive Self-supervised Transfer. The International Conference on Natural Language Processing and Chinese Computing (NLPCC), 2023, 616-628. (CCF C)

    4. YOU Peiwen, Jingjing Wang, GAO Xiaoya, LI Shoushan. Cross-modal Speech Sentiment Classification Based on Knowledge Distillation. Journal of Chinese Information Processing, 2023. (CCF B in Chinese Journal, Corresponding Author)

    2022

    1. Xiaoya Gao, Jingjing Wang, Shoushan Li, Min Zhang, Guodong Zhou. Cognition-driven multimodal personality classification. Journal of Science China and Information Sciences (Sci China Inf Sci, SCIS), 2022, 65(10). (CCF A, JCR Q1, Corresponding Author)

    2. YIN Yajue, GAO Xiaoya, Jingjing Wang, LI Shoushan, XU Shaoyang, ZENG Yuhao. Patent Matching with Multi-View Attentive Network. Journal of Chinese Information Processing, 2022, 36(7). (CCF B in Chinese Journal, Corresponding Author)

    3. ZHANG Yawei, WU Liangqing Jingjing Wang, LI Shoushan. Multi-modal Emotion Recognition Based on Multi-LSTMs Fusion. Journal of Chinese Information Processing, 2022, 36(5). (CCF B in Chinese Journal, Corresponding Author)

    2021

    1. Xiaoya Gao, Jingjing Wang, Shoushan Li, Guodong Zhou. Cognition-Driven Real-Time Personality Detection via Language-Guided Contrastive Visual Attention. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), 2021, 1-6. (CCF B, Corresponding Author)

    2. AN Minghui, Jingjing Wang, LIU Oiyuan, LI Lingin, ZHANG Daxin, LI Shoushan. Multimodal Hierarchical Dynamic Routing for Depression Detection. Journal of Chinese Information Processing, 2021. (CCF B in Chinese Journal, Corresponding Author)

    3. CHEN Xiao, Jingjing Wang, LI Shoushan, WEI Siyi, ZHANG Xiaoyu, CHEN Qiang. Cross lingual Aspect Sentiment Classification Based on Multi channel BERT. Journal of Chinese Information Processing, 2021. (CCF B in Chinese Journal, Corresponding Author)

    2020

    1. Xiao Chen, Changlong Sun, Jingjing Wang, Shoushan Li, Luo Si, Min Zhang, Guodong Zhou. Aspect Sentiment Classification with Document-level Sentiment Preference Modeling. Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2020, 3667-3677. (CCF A, Corresponding Author)

    2. Jingjing Wang, Jiancheng Wang, Changlong Sun, Shoushan Li, Xiaozhong Liu, Luo Si, Min Zhang, Guodong Zhou. Sentiment classification in customer service dialogue with topic-aware multi-task learning. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020, 9177-9184. (CCF A, Corresponding Author)

    3. Minghui An, Jingjing Wang, Shoushan Li, Guodong Zhou. Multimodal topic-enriched auxiliary learning for depression detection. In Proceedings of the International Conference on Computational Linguistics (COLING), 2020, 1078-1089. (CCF B, Corresponding Author)

    2019

    1. Jingjing Wang, Changlong Sun, Shoushan Li, Jiancheng Wang, Luo Si, Min Zhang, Xiaozhong Liu, Guodong Zhou. Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019, 5585-5594. (CCF B)

    2. Jingjing Wang, Changlong Sun, Shoushan Li, Xiaozhong Liu, Min Zhang, Luo Si, Guodong Zhou. Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network. Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL), 2019. (CCF A)

    3. Hanqian Wu, Shangbin Zhang, Jingjing Wang, Mumu Liu, Shoushan Li. Multi-label Aspect Classification on Question-Answering Text with Contextualized Attention-Based Neural Network. Proceedings of China Conference on Chinese Language Processing, 2019, 479-491. (EI, Corresponding Author)

    2018

    1. Jingjing Wang, Jie Li, Shoushan Li, Yangyang Kang, Min Zhang, Luo Si, Guodong Zhou. Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2018, 4439-4445. (CCF A)

    2. Jingjing Wang, Shoushan Li, Mingqi Jiang, Hanqian Wu, Guodong Zhou. Cross-media User Profiling with Joint Textual and Social User Embedding. In Proceedings of the International Conference on Computational Linguistics (COLING), 2018, 246-251. (CCF B)

    3. Chenlin Shen, Changlong Sun, Jingjing Wang, Yangyang Kang, Shoushan Li, Xiaozhong Liu, Luo Si, Min Zhang, Guodong Zhou. Sentiment Classification towards Question-Answering with Hierarchical Matching Network. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018, 3654-3663. (CCF B)

    4. Huan Liu, Jingjing Wang, Shoushan Li, Guodong Zhou. Semi-supervised Sentiment Classification Based on Auxiliary Task Learning. In Proceeding of the International Conference on Natural Language Processing and Chinese Computing (NLPCC), 2018. (CCF C)

    5. Hanqian Wu, Mumu Liu, Jingjing Wang, Jue Xie, Chenlin Shen. Question-Answering Aspect Classification with Hierarchical Attention Network. In Proceeding of China Conference on Chinese Language Processing, 2018, pp. 225-237. (EI, Corresponding Author)

    6. Hanqian Wu, Mumu Liu, Jingjing Wang, Jue Xie, Shoushan Li. Question-Answering Aspect Classification with Multi-attention Representation. In Proceeding of China Conference on Information Retrieval, 2018, pp.78-89. (EI)

    2017

    1. Jingjing Wang, Shoushan Li, Guodong Zhou. Joint Learning on Relevant User Attributes in Micro-blog. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2017, 4130-4136. (CCF A)

    2. Dong Zhang, Shoushan Li, Jingjing Wang. Semi-supervised Question Classification with Jointly Learning Question and Answer Representations. Journal of Chinese Information Processing, vol. 31(1), 2017. (CCF B in Chinese Journal)

    3. Jing Chen, Shoushan Li, Jingjing Wang, Guodong Zhou. User age prediction by combining classification and regression. Journal of Sci Sin Inform, 2017, 47: 1095–1108, doi: 10.1360/N112016-00278. (CCF A in Chinese Journal)

    2015

    1. Jingjing Wang, Yunxia Xue, Shoushan Li, Guodong Zhou. Leveraging Interactive Knowledge and Unlabeled Data in Gender Classification with Co-training. In Proceedings of the International Conference on Database Systems for Advanced Applications (DASFAA), 2015, 246-251. (CCF B)

    2. Shoushan Li, Jingjing Wang, Guodong Zhou, Hanxiao Shi. Interactive Gender Inference with Integer Linear Programming. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2015, 2341-2347. (CCF A)

    3. Shoushan Li, Lei Huang, Jingjing Wang, Guodong Zhou. Semi-Stacking for Semi-supervised Sentiment Classification. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2015, 27-31. (CCF A)

    4. Lei Huang, Shoushan Li, Jingjing Wang. User-Type Classification in Micro-Blog Based on Information of Authenticated User. Journal of Frontiers of Computer Science and Technology, vol. 9(6), 2015. (CCF B in Chinese Journal)

    5. Jingjing Wang, Shoushan Li, Lei Huang. User Gender Classification in Chinese Microblog. Journal of Chinese Information Processing, vol. 28(6), 2014. (CCF B in Chinese Journal)

    6. Zhu zhu, Jingjing Wang, Shoushan Li, Guodong Zhou. Interactive Gender Inference in Social Media. In Proceedings of the International Conference on Database Systems for Advanced Applications (DASFAA), 2015, 252-258. (CCF B)

    Awards & Honors

    • Outstanding Expert and Supervisor of Microsoft (2022)

    • Outstanding PhD of Soochow University (2019)

    • Suzhou Industrial Park Scholarship (2018)

    • National Scholarship for Ph.D. (2017)

    • Ph.D. Scholarship of Soochow University (2017)

    • National Scholarship for Master (2016)

    • Outstanding Graduate Student of Soochow University (2016)

    • Suzhou Industrial Park Scholarship (2015)

    • etc.

    Academic Services

    • Technical Program Committee (Area Chair & PC)

    • ACL: Annual Meeting of the Association for Computational Linguistics, Area Chair

    • EMNLP: Conference on Empirical Methods in Natural Language Processing, Area Chair

    • AAAI: Association for the Advancement of Artificial Intelligence, PC

    • IJCAI: International Joint Conference on Artificial Intelligence, PC

    • etc.

    • Journal Reviewer

    • TASLP: IEEE/ACM Transactions on Audio, Speech, and Language Processing

    • TALLIP: ACM Transactions on Asian and Low-Resource Language Information Processing

    • SCIS: Science China Information Sciences

    • Science China

    • Acta Automatica Sinica

    • Journal of Chinese Information Processing

    • etc.

    • Academic Presentations and Exchanges

    • 2016-2021: Academic reports and exchanges at top conferences including ACL, AAAI, IJCAI

    • 2019: Academic report and exchange at Zhejiang Tailong Commercial Bank, Suzhou Industrial Park Headquarters

    • 2019: Invited talk at Ecovacs, Suzhou

    • 2022: Academic report and exchange at Alibaba Ant Financial

    • 2023: Academic report and exchange at the establishment of NLPAI-SCHOOL, Microsoft Asia Engineering Institute, Suzhou

    • etc.

    Research Grants

      As Principle Investigator

      1. Key Technology Research on Attribute-level Sentiment Analysis for Conversational Texts (No. 62006166: 240K RMB: 2021.01–2023.12)
        Supported by the National Natural Science Foundation of China (NSFC Young Scientist Fund Project)

      2. Research on Chinese Single-document Automatic Summarization Based on Discourse Structure Analysis (No. 61976146: 560K RMB: 2020.01–2023.12)
        Supported by the National Natural Science Foundation of China (NSFC General Program)

      3. Resource Construction and Key Technology Research on Sentiment Information Extraction from Question-answer Texts (No. 2019M661930: 80K RMB: 2020.01–2022.12)
        Supported by China Postdoctoral Science Foundation (CPSF)

      As Co-investigator

      1. Scene-based Knowledge Graph for Language Understanding and Generation (Sub-project No. 2020AAA0108604: 6,650K RMB: 2020.11–2023.10)
        Supported by the National Key Research and Development Program