Roy Xie

I am a Computer Science Ph.D. student at Duke University, advised by Bhuwan Dhingra. My research area is natural language processing, with a focus on large language models and adversarial attacks.

Before joining Duke, I completed my undergraduate studies at George Mason University, where I worked with Antonios Anastasopoulos on multilingual NLP.

 /   /   /   /   

profile photo

Research

My research interests span various aspects of natural language processing and machine learning, focusing on building safe, interpretable, and efficient language technologies for social good.

LLM-Resistant Math Word Problem Generation via Adversarial Attacks
Roy Xie, Chengxuan Huang, Junlin Wang, Bhuwan Dhingra
Preprint, 2024

A novel approach to generate math word problems that LLMs are unable to solve, while preserving the coherence and difficulty of the original problems.

Raccon: Prompt Extraction Benchmark of LLM-Integrated Applications
Junlin Wang, Tianyi Yang, Roy Xie, Bhuwan Dhingra
Under review, 2024

A benchmark which comprehensively evaluates a LLM’s susceptibility to prompt extraction attacks.

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
Under review, 2024

A comprehensive dataset for training and evaluating models for tailoring vaccine messaging to opinions to establish common ground.

Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers
Roy Xie, Orevaoghene Ahia, Yulia Tsvetkov, Antonios Anastasopoulos
Preprint, 2024

Extract lexical features from language dialects through interpretable dialect classifiers.

GMNLP at SemEval-2023 Task 12: Sentiment Analysis with Phylogeny-Based Adapters
Md Mahfuz Ibn Alam∗, Roy Xie∗, Fahim Faisal∗, Antonios Anastasopoulos
SemEval@ACL, 2023

A sentiment analysis system for low-resource African languages, leveraging multilingual language models, data augmentation method, and phylogeny-based adapter-tuning.

Noisy Parallel Data Alignment
Roy Xie and Antonios Anastasopoulos
EACL Findings, 2023

Make word-level alignment models more robust under OCR noisy setting by using noise simulation and structural bias.



Website template