News
Dec 2024
One paper is accepted by AAAI'25 about Combating Misinformation in RAG .
Oct 2024
MMDocBench is released, which is designed to evaluate large vision-language models(LVLMs) in fine-grained visual document understanding.
Sep 2024
One paper is accepted by ICAIF'24 (Oral) about LLM training and specialization for understanding and reasoning over financial table-text data.
Sep 2024
One paper is accepted by EMNLP'24 Findings about prompt tuning, robust prompt optimization, and trustiness of large language models (LLMs).
Feb 2024
One paper is accepted by LREC-COLING'24 about Graph-based representation for understanding and reasoning over financial table-text data.
Fengbin Zhu
Postdoctoral Research Fellow
NExT++
COM4, 3A Research Link, Singapore 119392
Email: zhfengbin AT gmail.com
|
I am a Postdoc Research Fellow at NExT Research Center National University of Singapore (NUS), working with Prof. Tat-Seng Chua. I earned my PhD from NUS in June 2024, also supervised by Prof. Chua. My research interests include Natural Language Processing (NLP), Information Retrieval (IR), Document Intelligence (DI), and the application of AI in finance.
PS: I am actively looking for highly motivated PhD/master/undergraduate students to collaborate on various interesting research topics, including retrieval-augmented generation, multi-modal LLM for document intelligence, financial LLM, and LLM-based agents, etc. If you have interest, please feel free to send your CV to zhfengbin@gmail.com.
Publications Google Scholar
#Equal Contribution *Corresponding AuthorMMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding
Fengbin Zhu, Ziyang Liu, Xiang Yao NG, Haohui Wu, Wenjie Wang, Fuli Feng, Chao Wang, Huanbo Luan, and Tat-Seng Chua Arxiv 2024 |
Large Language Models Empowered Personalized Web Agents
Hongru Cai, Yongqi Li, Wenjie Wang, Fengbin Zhu, Xiaoyu Shen, Wenjie Li, and Tat-Seng Chua Arxiv 2024 |
Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector
Youcheng Huang#, Fengbin Zhu#, Jingkun Tang, Pan Zhou, Wenqiang Lei, and Tat-Seng Chua Arxiv 2024 |
TAT-LLM: A Specialized Language Model for Discrete Reasoning over Financial Tabular and Textual Data
Fengbin Zhu, Ziyang Liu, Fuli Feng, Chao Wang, Moxin Li and Tat-Seng Chua ICAIF 2024 (Oral) |
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG
Boyi Deng, Wenjie Wang, Fengbin Zhu, Qifan Wang, and Fuli Feng AAAI 2025 |
VideoQA in the Era of LLMs: An Empirical Study
Junbin Xiao, Nanxin Huang, Hangyu Qin, Dongyang Li, Yicong Li, Fengbin Zhu, Zhulin Tao, Jianxing Yu, Liang Lin, Tat-Seng Chua, Angela Yao Arxiv 2024 |
Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection
Moxin Li, Wenjie Wang, Fuli Feng, Fengbin Zhu, Qifan Wang, Tat-Seng Chua EMNLP 2024 (Findings) |
Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs
Fengbin Zhu, Chao Wang, Fuli Feng, Zifeng Ren, Moxin Li, Tat-Seng Chua LREC-COLING 2024 (Poster) |
SoarGraph: Numerical Reasoning over Financial Table-Text Data via Semantic-Oriented Hierarchical Graphs
Fengbin Zhu, Moxin Li, Junbin Xiao, Fuli Feng, Chao Wang, Tat Seng Chua WWW 2023 (Workshop) |
Towards Complex Document Understanding By Discrete Reasoning
Fengbin Zhu, Wenqiang Lei, Fuli Feng, Chao Wang, Haozhou Zhang, Tat-Seng Chua ACM MM 2022 (Poster) |
RDU: A Region-based Approach to Form-style Document Understanding
Fengbin Zhu, Chao Wang, Wenqiang Lei, Ziyang Liu, Tat Seng Chua Arxiv 2022 |
Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete Reasoning
Moxin Li, Fuli Feng, Hanwang Zhang, Xiangnan He, Fengbin Zhu, Tat-Seng Chua ACL 2022 (Poster) |
TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance
Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, Tat-Seng Chua ACL 2021 (Oral) |
Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
Fengbin Zhu, Wenqiang Lei, Chao Wang, Jianming Zheng, Soujanya Poria, Tat-Seng Chua Arxiv 2021 |
Professional Services
Program Committee Member of ACMMM (2022), ACMMM (2023), ACMMM (2024) Program Committee Member of AAAI (2023), AAAI (2024) Program Committee Member of ACL ARR (2024) Program Committee Member of COLING (2025) Invited Reviewer for ACM Transactions on Information Systems (TOIS) |
Education
National University of Singapore (NUS) Ph.D. in Computer Science Aug 2019 - Jun 2024, Singapore Advisor: Prof. Tat-Seng Chua Mentors: Prof. Fuli Feng, Prof. Wenqiang Lei and Dr. Chao Wang |
Experiences
Postdoc Research Fellow, National University of Singapore, Jul 2024 - Present Advisior: Prof. Tat-Seng Chua (NExT++: NUS-Tsinghua-Southampton Extreme Search Center) |
Technology Director, 6Estates Pte Ltd, Mar 2015 - Jun 2024 |
Research Assistant, National University of Singapore, Mar 2012 - Mar 2015 Advisior: Prof. Tat-Seng Chua (NExT: NUS-Tsinghua Extreme Search Center) |
Selected Awards
Research Achievement Award, 2022
- School of Computing, National University of Singapore |
Winner of 1st Competition on Chinese Machine Reading Comprehension (CMRC), 2017
- 16th China National Conference on Computational Linguistics (CCL) |
Last update: Oct, 2024. Webpage template borrows from Prof. Fuli Feng and Prof. Xiangnan He.