Bo Wang

Title:Assistant Professor

Education: Jilin University

Email:bowang97@jlu.edu.cn

Homepage:

Research Areas:Trustworthy AI, Natural Language Processing

About Me

Bo Wang is an Assistant Professor and Ph.D. supervisor at the School of Artificial Intelligence, Jilin University. She received her Ph.D. from the same institution in 2026 under the supervision of Professor Yi Chang. Her research focuses on trustworthyAIand natural language processing, including the security and privacy of large language models and AI agents, retrieval-augmented generation, andfakenews detection. She has published more than ten papers in leading international conferences and journals, including ACL, WWW, EMNLP, and ACM TOIS, with over 1,000 citations on Google Scholar. She is the principal investigator of a Young Student Basic Research Project funded by the National Natural Science Foundation of China.

Reseach

1.Bo Wang,Jing Ma*, Hongzhan Lin, Zhiwei Yang, Ruichao Yang, Yuan Tian*, Yi Chang*. A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM. ACM Transactions on Information Systems (TOIS), 2026, 44(5): 1-36. (CCF-A)

2.Bo Wang,Weiyi He, Shenglai Zeng, Zhen Xiang, Yue Xing, Jiliang Tang, Pengfei He*. Unveiling Privacy Risks in LLM Agent Memory. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL) 2025: 25241-25260. (CCF-A)

3.Bo Wang, Jing Ma*, Hongzhan Lin, Zhiwei Yang, Ruichao Yang, Yuan Tian*, Yi Chang*. Explainable Fake News Detection with Large Language Model via Defense Among Competing Wisdom. In Proceedings of the ACM Web Conference 2024 (WWW). 2024:2452-2463. (CCF-A)

4.Bo Wang,Tao Shen, Guodong Long, Tianyi Zhou, Yi Chang*. Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2021. (EMNLP) 2021: 3002-3012. (CCF-B)

5.Bo Wang, Tao Shen, Guodong Long, Tianyi Zhou, Ying Wang*, Yi Chang*. Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion. In Proceedings of the ACM Web Conference 2021 (WWW). 2021: 1737-1748. (CCF-A)

6.Hongzhan Lin, Wei Gao, Yang Deng, Ziyang Luo,Bo Wang, Ruichao Yang, Jing Ma*, Tat-Seng Chua. EXPLAINHM++: Explainable Harmful Meme Detection with Retrieval-Augmented Debate between Large Multimodal Models. IEEE Transactions on Knowledge and Data Engineering (TKDE). (CCF-A)

7.Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma*,Bo Wang, Ruichao Yang. Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models.WWW2024. (CCF-A)

8.Ruichao Yang, Wei Gao, Jing Ma*, Hongzhan Lin,Bo Wang. Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models.ACL(Findings) 2024. (CCF-A)

9.Hongzhan Lin, Ziyang Luo,Bo Wang, Ruichao Yang, Jing Ma*. Goat-bench: Safety insights to large multimodal models through meme-based social abuse. ACM Transactions on Intelligent Systems and Technology (TIST), 2024.

10.Yuxiang Ren,Bo Wang, Jiawei Zhang, Yi Chang. Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection.ICDM2020. (CCF-B)

return