Hai Wang

Researcher, Amazon

Joined

October 2016

Names

Hai Wang (Preferred)

Emails

****@ttic.edu (Confirmed)

****@amazon.com (Confirmed)

Personal Links

Homepage

Google Scholar

ORCID

Career & Education History

Researcher

Amazon (amazon.com)

2024 – Present

Researcher

Samsung Research America (samsung.com)

2023 – 2024

PhD student

Toyota Technological Institute at Chicago (ttic.edu)

2014 – 2020

Advisors, Relations & Conflicts

PhD Advisor

David McAllester

2014 – 2020

Expertise

Natural Language Processing

2015 – Present

Machine Learning

2011 – Present

Publications

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
- NeurIPS 2023 BUGS Oral
- Readers: Everyone
Instruction-following Evaluation through Verbalizer Manipulation
Shiyang Li, Jun Yan, Hai Wang, Zheng Tang, Xiang Ren, Vijay Srinivasan, Hongxia Jin
- Instruction Workshop @ NeurIPS 2023
- Readers: Everyone
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
AlpaGasus: Training a Better Alpaca with Fewer Data
Lichang Chen, Shiyang Li, Jun Yan, Hai Wang, Kalpa Gunaratna, Vikas Yadav, Zheng Tang, Vijay Srinivasan, Tianyi Zhou, Heng Huang, Hongxia Jin
- ICLR 2024 poster
- Readers: Everyone
Instruction-following Evaluation through Verbalizer Manipulation
Shiyang Li, Jun Yan, Hai Wang, Zheng Tang, Xiang Ren, Vijay Srinivasan, Hongxia Jin
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
AlpaGasus: Training A Better Alpaca with Fewer Data
Lichang Chen, Shiyang Li, Jun Yan, Hai Wang, Vikas Yadav, Kalpa Gunaratna, Zheng Tang, Vijay Srinivasan, Tianyi Zhou, Heng Huang, Hongxia Jin
- 31 Jul 2023 (modified: 31 Jul 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone
Improving Pre-Trained Multilingual Models with Vocabulary Expansion
Hai Wang
- 14 Oct 2021
- OpenReview Archive Direct Upload
- Readers: Everyone
Evidence Extraction for Machine Reading Comprehension
Hai Wang
- 14 Oct 2021
- OpenReview Archive Direct Upload
- Readers: Everyone
Deep Probabilistic Logic: A Unifying Framework for Indirect Supervision
Hai Wang, Hoifung Poon
- 2018 (modified: 16 Jul 2019)
- EMNLP 2018
- Readers: Everyone
Who did What: A Large-Scale Person-Centered Cloze Dataset
Takeshi Onishi, Hai Wang, Mohit Bansal, Kevin Gimpel, David A. McAllester
- 2016 (modified: 16 Jul 2019)
- EMNLP 2016
- Readers: Everyone

View all 11 publications