Shenglai Zeng

PhD Student

DSE Lab
Department of Computer Science
Michigan State University
Email: zengshe1 [at] msu [dot] edu


About Me

Hi there, my name is Shenglai Zeng. Currently, I am a third-year Ph.D. student from Michigan State University, advised by professor Jiliang Tang. Previously, I received my bachelor degree with highest honnor from Yingcai Honor School at University of Electronic Science and Technology of China. I was also a research intern of Amazon Search at 2025-Fall, 2024-Fall, Baidu at 2023-Fall, The University of British Columbia at 22-Fall, Peen State University at 2021-Fall. I have won the Best Paper Award of IEEE Transactions on Cloud Computing, 2023

Research Topics

My current research interests are mainly about Trustworthy AI, Large language models(LLMs) and Information Retrieval. Previously, I focused on federated learning.


News

[9/2025] 1 paper is accepted by NeurIPS 2025. Congratulations to all co-authors!
[8/2025] 3 papers are accepted by EMNLP 2025(main). Congratulations to all co-authors!
[5/2025] 2 papers are accepted by ACL 2025(main). Congratulations to all co-authors!
[5/2025] 1 paper is accepted by KDD 2025. Congratulations to all co-authors!
[3/2025] One paper is accepted by CVPR 2025. Congratulations to all co-authors!
[3/2025] Our paper: Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective is accepted as Oral paper at NAACL main conference!
[12/2024] Our paper: Hfedms: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse was awarded the 2023 Best Paper Award from IEEE Transactions on Cloud Computing
[8/2024] One paper has got accepted by TMLR! Congrats to all co-authors
[8/2024] One paper has got accepted by EMNLP-2024! Congrats to all co-authors
[6/2024] One paper has got accepted by ECCV-2024! Congrats to all co-authors
[5/2024] Begin my internship at Amazon Search!
[5/2024] Our paper: Exploring Memorization in Fine-tuned Language Models has got ACL-2024 Acceptance! Congrats to all co-authors!
[5/2024] Our paper: The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) has got ACL-2024 Acceptance! Congrats to all co-authors!
[2/2024] We preprint our paper: The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
[2/2023] We preprint our paper: Copyright Protection in Generative AI: A Technical Perspective
[2/2023] Our paper: Sharpness-Aware Data Poisoning Attack has got ICLR-2024 Spotlight! Congrats to all co-authors!
[10/2023] We preprint our paper: Exploring Memorization in Fine-tuned Language Models!
[9/2023] Began my PhD at DSE lab, Michigan State University! New journey!
[6/2023] Began my Intership at Baidu.Inc!
[2/2023] One paper is accepted by IEEE Transactions on Cloud Computing!
[12/2022] One paper was accepted by SDM 2023, thanks to my co-authors!
[12/2022] Our HFedMS submitted to TCC received major revision, good news!
[10/2021] I was awarded the most outstanding undergraduate students in UESTC, which is the highest honor awarded to only 10 students in UESTC
[10/2022] One paper was submitted to IEEE Transaction on Cloud Computing
[9/2022] One paper was submitted to SDM 2023 on semi-supervised FL design for IoT devices.
[7/2022] I was invited to serve as a PC Member for MICCAI Workshop on Distributed, Collaborative and Federated Learning (DeCaF)
[6/2022] Began my remote summer internship at The University of British Columbia
[4/2022] Made an online presentation on DASFAA2022, great experience!
[1/2022] Our paper "Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training" was accepted by DASFAA2022, thanks to my co-authors!
[10/2021] I was awarded WAC Scholarship(10 students among all students in UESTC)
[6/2021] Began my remote summer internship at Peen State University, Park
[4/2021] Submitted a national patent on the optimazation of federated learning
[10/2020] I was awarded National Scholarship by Ministry of Education


Selected Publications

Preprints

Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs
Shenglai Zeng, Tianqi Zheng, Chuan Tian, Dante Everaert, Yau-Shian Wang, Yupin Huang, Michael J. Morais, Rohit Patki, Jinjin Tian, Xinnan Dai, Kai Guo, Monica Xiao Cheng, Hui Liu
Preprint
[Paper]

Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
Kai Guo, Xinnan Dai, Shenglai Zeng, Harry Shomer, Haoyu Han, Yu Wang, Jiliang Tang
Preprint
[Paper]

Copyright Protection in Generative AI: A Technical Perspective
Jie Ren, Han Xu, Pengfei He, Yingqian Cui, Shenglai Zeng, Jiankun Zhang, Hongzhi Wen, Jiayuan Ding, Hui Liu, Yi Chang, Jiliang Tang
Preprint
[Paper]

GraphGhosts: Tracing Reasoning Structures Behind Large Language Models
Xinnan Dai, Kai Guo, Chung-Hsiang Lo, Shenglai Zeng, Jiayuan Ding, Dongsheng Luo, Subhabrata Mukherjee, Jiliang Tang
Preprint
[Paper]

Publications

2025

Mitigating the privacy issues in retrieval-augmented generation (rag) via pure synthetic data
Shenglai Zeng, Jiankun Zhang, Pengfei He, Jie Ren, Tianqi Zheng, Hanqing Lu, Han Xu, Hui Liu, Yue Xing, Jiliang Tang
EMNLP 2025(main)
[Paper]

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
Jiankun Zhang*, Shenglai Zeng*, Jie Ren, Tianqi Zheng, Hui Liu, Xianfeng Tang, Yi Chang
EMNLP 2025(main)
[Paper]

Empowering GraphRAG with Knowledge Filtering and Integration
Kai Guo, Harry Shomer, Shenglai Zeng, Haoyu Han, Yu Wang, Jiliang Tang
EMNLP 2025(main)
[Paper]

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
Jie Ren, Zhenwei Dai, Xianfeng Tang, Yue Xing, Shenglai Zeng, Hui Liu, Jingying Zeng, Qiankun Peng, Samarth Varshney, Suhang Wang, Qi He, Charu C. Aggarwal, Hui Liu
NeurIPS 2025
[Paper]

Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach
Shenglai Zeng, Pengfei He, Kai Guo, Tianqi Zheng, Hanqing Lu, Yue Xing, Hui Liu
ACL 2025(main)
[Paper]

Unveiling privacy risks in llm agent memory
Bo Wang, Weiyi He, Pengfei He, Shenglai Zeng, Zhen Xiang, Yue Xing, Jiliang Tang
ACL 2025(main)
[Paper]

Unveiling Mode Connectivity in Graph Neural Networks
Bingheng Li, Zhikai Chen, Haoyu Han, Shenglai Zeng, Jingzhe Liu, Jiliang Tang
KDD 2025
[Paper]

Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective
Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Yue Xing, Monica Xiao Cheng, Jiliang Tang
NAACL 2025(Oral)
[Paper]

Six-cd: Benchmarking concept removals for benign text-to-image diffusion models
Jie Ren, Kangrui Chen, Yingqian Cui, Shenglai Zeng, Hui Liu, Yue Xing, Jiliang Tang, Lingjuan Lyu
CVPR 2025
[Paper]

Stealthy Backdoor Attack via Confidence-driven Sampling
Pengfei He, Yue Xing, Han Xu, Jie Ren, Yingqian Cui,Shenglai Zeng, Jiliang Tang, Makoto Yamada, Mohammad Sabokrou
TMLR
[Paper]

2024

On the Generalization of Training-based ChatGPT Detection Methods
Han Xu,Jie Ren,Pengfei He, Yingqian Cui, Shenglai Zeng, Hui Liu, Jiliang Tang, Amy Liu
EMNLP 2024(Findings)
[Paper]

Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention
Jie Ren, Yaxin Li, Shenglai Zeng, Han Xu, Lingjuan Lyu, Yue Xing, Jiliang Tang
ECCV-2024
[Paper]

Exploring Memorization in Fine-tuned Language Models
Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Shuaiqiang Wang, Jiliang Tang, Dawei Yin
ACL-2024(main)
[Paper]

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
Shenglai Zeng, Jiankun Zhang, Pengfei He, Yue Xing, Yiding Liu, Han Xu, Jie Ren, Shuaiqiang Wang, Dawei Yin, Yi Chang, Jiliang Tang
ACL 2024(Findings)
[Paper]

Sharpness-Aware Data Poisoning Attack
Pengfei He, Han Xu, Jie Ren, Yingqian Cui, Shenglai Zeng, Hui Liu, Charu C. Aggarwal, Jiliang Tang
ICLR-2024 (Spotlight)
[Paper]

2023 and earlier

Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
Juanhui Li, Harry shomer, Haitao Mao, Shenglai Zeng, Yao Ma,Neil Shah, Jiliang Tang, Dawei Yin
NeurIPS 2023
[Paper]

HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse
Shenglai Zeng, Zonghang Li, Hongfang Yu, Zhihao Zhang, Long Luo, Bo Li, Dusit Niyato
IEEE Transaction on Cloud Computing, 2023 Best Paper Award
[Paper]

Knowledge-Enhanced Semi-Supervised Federated Learning for Aggregating Heterogeneous Lightweight Clients in IoT
Jiaqi Wang*, Shenglai Zeng*, Zewei Long, Yaqing Wang, Houping Xiao, Fenglong Ma
SDM 2023
[Paper]

Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training
Shenglai Zeng, Zonghang Li, Hongfang Yu, Yihong He, Zenglin Xu, Dusit Niyato and Han Yu
DASFAA 2022
[Paper] [Video]



Experience

Amazon, Palo Alto, CA

       Applied Scientist Intern,   Summer 2024,2025

       Mentors: Tianqi Zheng, Chuan Shi, Dante Everaert, Hanqing Lu, Monica Xiao Cheng

       Collaborators: Xianfeng Tang, Hui Liu, Rohit Patk Jinjin Tian, Yau-Shian Wan, Yupin Huang, Michael J. Morais

       Projects 2024: Retrieval-augemented Generation(RAG). Pubilished 4 papers. Knowledge Checking in RAG(NAACL-25, oral), Representation Finetuning for Robust RAG(ACL-25)), Synthetic Data for RAG (EMNLP-25), Multi-modal RAG (EMNLP-25)

       Projects 2025: Efficient Personalized LLMs(PLLMs). Attention-guided context compression for efficent PLLMs(Submitted to ARR)

Baidu.Inc, Beijing, China

       Research Intern,   Summer 2023

       Mentor: Yiding Liu, Dawei Yin

       Projetcs: LLM Memorization (ACL-24), RAG Privacy(ACL-24)

The University of British Columbia, Vancouver, Canada

       Research Intern(MITACS program),   Summer 2022

       Mentor: Xiaoxiao Li

The Pennsylvania State University, Pennsylvania, US

       Research Intern,   Summer 2021

       Mentor: Fenglong Ma

The University of Chicago, Chicago, US

       Online Intern,   Mar 2020-Mar 2021

       Mentor: Shinan Liu



Selected Awards

  • Best Paper Award, IEEE Transactions on Cloud Computing, 2023

  • Spotlight Paper Award, ICLR, 2024

  • The Most Outstanding Students Award of UESTC(Highest honor in UESTC, Only10 students are awarded) , 2024

  • National Scholarship(Highest honor of undergraduate student), 2020



  • Service

  • Conference Program Committee or Reviewer: ACL-ARR,NIPS,ICLR, IEEE TMC, IEEE Trans on Service Computing, IEEE TPDS, IEEE TKDE, IoT-J, IEEE Trans on Information Forensics & Security, MICCAI Workshop on Distributed, Collaborative and Federated Learning (DeCaF-2022), The ACM Transactions on Information Systems (TOIS),IEEE Transactions on Vehicular Technology(TVT),IEEE TKDD

  • visitors