Zexuan Zhong

Researcher, Facebook

Joined

July 2019

Names

Zexuan Zhong

Emails

****@princeton.edu (Confirmed)

****@cs.princeton.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Researcher

Facebook (meta.com)

2025 – Present

PhD student

Princeton University (princeton.edu)

2019 – 2024

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Certifiably Robust RAG against Retrieval Corruption Attacks
Chong Xiang, Tong Wu, Zexuan Zhong, David Wagner, Danqi Chen, Prateek Mittal
- Submitted to ICLR 2025
- Readers: Everyone
Certifiably Robust RAG against Retrieval Corruption
Chong Xiang, Tong Wu, Zexuan Zhong, David Wagner, Danqi Chen, Prateek Mittal
- NextGenAISafety 2024 Poster
- Readers: Everyone
Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training
Zexuan Zhong, Mengzhou Xia, Danqi Chen, Mike Lewis
- COLM
- Readers: Everyone
Structured Pruning Learns Compact and Accurate Models
Mengzhou Xia, Zexuan Zhong, Danqi Chen
- 04 Jul 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Poisoning Retrieval Corpora by Injecting Adversarial Passages
Zexuan Zhong, Ziqing Huang, Alexander Wettig, Danqi Chen
- EMNLP 2023 Main
- Readers: Everyone
Privacy Implications of Retrieval-Based Language Models
Yangsibo Huang, Samyak Gupta, Zexuan Zhong, Kai Li, Danqi Chen
- EMNLP 2023 Main
- Readers: Everyone
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
Zexuan Zhong, Zhengxuan Wu, Christopher D Manning, Christopher Potts, Danqi Chen
- EMNLP 2023 Main
- Readers: Everyone
Training language models with memory augmentation
Zexuan Zhong, Tao Lei, Danqi Chen
- 15 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Models
Yangsibo Huang, Daogao Liu, Zexuan Zhong, Weijia Shi, Yin Tat Lee
- 2023 (modified: 24 Apr 2023)
- CoRR 2023
- Readers: Everyone
Recovering Private Text in Federated Learning of Language Models
Samyak Gupta, Yangsibo Huang, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone

View all 30 publications

Co-Authors

View all 41 co-authors