Roy Xie Small Image

Duke University

I am a first-year Computer Science Ph.D. student at Duke University, advised by Bhuwan Dhingra. I study the properties of language models from an adversarial perspective. My recent work focuses on developing attacks and evaluation strategies to assess the robustness and limitations of LLMs.

My research is supported by the NSF Graduate Research Fellowship. Previously, I completed my undergraduate degree at George Mason University, where I worked with Antonios Anastasopoulos on multilingual NLP.

I am open to collaborations. If you have a cool idea that you would like to discuss or simply want to chat about research, please feel free to email me!

 /   /   /   /   




profile photo

Research

My research interests span various aspects of natural language processing and machine learning, focusing on building safe, interpretable, and robust language technologies for social good.
Publication Image
LLM-Resistant Math Word Problem Generation via Adversarial Attacks
Roy Xie, Chengxuan Huang, Junlin Wang, Bhuwan Dhingra
Preprint, 2024
Publication Image
Raccon: Prompt Extraction Benchmark of LLM-Integrated Applications
Junlin Wang, Tianyi Yang, Roy Xie, Bhuwan Dhingra
ACL Findings, 2024
Publication Image
Tailoring Vaccine Messaging with Common-Ground Opinions
Rickard Stureborg, Sanxing Chen, Roy Xie, Aayushi Kunjal Patel, Christopher Li, Chloe Zhu, Tingnan Hu, Jun Yang, Bhuwan Dhingra
NAACL Findings, 2024
Publication Image
Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers
Roy Xie, Orevaoghene Ahia, Yulia Tsvetkov, Antonios Anastasopoulos
NAACL, 2024
Publication Image
GMNLP at SemEval-2023 Task 12: Sentiment Analysis with Phylogeny-Based Adapters
Md Mahfuz Ibn Alam, Roy Xie, Fahim Faisal, Antonios Anastasopoulos
ACL SemEval, 2023
Publication Image
Noisy Parallel Data Alignment
Roy Xie, Antonios Anastasopoulos
EACL Findings, 2023

Service

Reviewer: ACL, EMNLP, ACL Rolling Review

Organizer: MASC-SLL 2023