Hengzhi Pei

Joined

November 2019

Names

Hengzhi Pei (Preferred)

Emails

****@fudan.edu.cn (Confirmed)

****@illinois.edu (Confirmed)

****@amazon.com (Confirmed)

Personal Links

Career & Education History

Applied Scientist

Amazon (amazon.com)

2023 – 2025

MS student

University of Illinois, Urbana Champaign (illinois.edu)

2021 – 2023

Research Assistant

Microsoft Research Asia (microsoft.com)

2020 – 2021

Undergrad student

Fudan University (fudan.edu)

2016 – 2020

Advisors, Relations & Conflicts

No relations added

Expertise

Natural Language Processing

Present

Adversarial Machine Learning

Present

Publications

Knowledge Distillation for Large Language Models through Residual Learning
Thinh On, Hengzhi Pei, Leonard Lausen, George Karypis
- ICLR 2026 Poster
- Readers: Everyone
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
- NeurIPS 2023 Datasets and Benchmarks Oral
- Readers: Everyone
Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion
Hengzhi Pei, Jinman Zhao, Leonard Lausen, Sheng Zha, George Karypis
- AAAI 2023
- Readers: Everyone
TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Hengzhi Pei, Jinyuan Jia, Wenbo Guo, Bo Li, Dawn Song
- CoRR 2023
- Readers: Everyone
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Chi Han, Hengzhi Pei, Xinya Du, Heng Ji
- ACL (Findings) 2023
- Readers: Everyone
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
- NeurIPS 2023
- Readers: Everyone
E-Forcing: Improving Autoregressive Models by Treating it as an Energy-Based One
Yezhen Wang, Tong Che, Bo Li, Kaitao Song, Hengzhi Pei, Yoshua Bengio, Dongsheng Li
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Improving Certified Robustness via Statistical Learning with Logical Reasoning
Zhuolin Yang, Zhikuan Zhao, Boxin Wang, Jiawei Zhang, Linyi Li, Hengzhi Pei, Bojan Karlaš, Ji Liu, Heng Guo, Ce Zhang, Bo Li
- Published: 31 Oct 2022, Last Modified: 13 Oct 2022
- NeurIPS 2022 Accept
- Readers: Everyone
Improving Certified Robustness via Statistical Learning with Logical Reasoning
Zhuolin Yang, Zhikuan Zhao, Boxin Wang, Jiawei Zhang, Linyi Li, Hengzhi Pei, Bojan Karlas, Ji Liu, Heng Guo, Ce Zhang, Bo Li
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- NeurIPS 2022
- Readers: Everyone
YOUR AUTOREGRESSIVE GENERATIVE MODEL CAN BE BETTER IF YOU TREAT IT AS AN ENERGY-BASED ONE
Yezhen Wang, Tong Che, Bo Li, Kaitao Song, Hengzhi Pei, Yoshua Bengio, Dongsheng Li
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Submitted
- Readers: Everyone

View all 15 publications

Co-Authors

View all 59 co-authors