Roy Xie Small Image

Duke University

I am a second-year Computer Science Ph.D. student at Duke NLP, advised by Bhuwan Dhingra. My research mainly focuses on post-training methods for LLMs. I am particularly interested in improving LLMs reasoning ability and developing RL-based agents, especially for complex multi-hop tasks.

My research is supported by the 2025 Apple Scholars in AI/ML Ph.D. Fellowship and the 2024 National Science Foundation Graduate Research Fellowship. Before Duke, I worked with Antonios Anastasopoulos on low-resource NLP.

                




profile photo

Recent Publications

Publication Image
Interleaved Reasoning for Large Language Models via Reinforcement Learning
Roy Xie, David Qiu, Deepak Gopinath, Dong Lin, Yanchao Sun, Chong Wang, Saloni Potdar, Bhuwan Dhingra
Preprint, 2025
Publication Image
Knowing When to Stop: Dynamic Context Cutoff for Large Language Models
Roy Xie, Junlin Wang, Paul Rosu, Chunyuan Deng, Bolun Sun, Zihao Lin, Bhuwan Dhingra
Preprint, 2025
Publication Image
Improving Model Alignment Through Collective Intelligence of Open-Source Models
Junlin Wang, Roy Xie, Shang Zhu, Jue Wang, Ben Athiwaratkun, Bhuwan Dhingra, Shuaiwen Leon Song, Ce Zhang, James Zou
ICML, 2025
Publication Image
ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods
Roy Xie, Junlin Wang, Ruomin Huang, Minxing Zhang, Rong Ge, Jian Pei, Neil Gong, Bhuwan Dhingra
EMNLP, 2024
Publication Image
Adversarial Math Word Problem Generation
Roy Xie, Chengxuan Huang, Junlin Wang, Bhuwan Dhingra
EMNLP Findings, 2024
Publication Image
Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers
Roy Xie, Orevaoghene Ahia, Yulia Tsvetkov, Antonios Anastasopoulos
NAACL, 2024