Welcome
About me
Hello! I’m Bang, a third-year Ph.D. student (2022-now) in the Computer Science and Engineering department at the University of Notre Dame. I’m fortunate to be a member of the Data Mining towards Decision Making (DM2) Lab, where I am advised by Dr. Meng Jiang.
I obtained my Bachelor’s Degree from The College of Wooster in 2022 with a major in Computer Science and a double minor in Data Science and Communication Studies.
With a strong interest in Natural Language Processing (NLP) and Machine Learning, my research focuses on simulation-based evaluation of NLP applications. I am currently exploring how simulated classroom learning can facilitate the development and evaluation of AI tutors. My work aims to improve how AI systems can align with human behaviors and values, ensuring that they support users in achieving their goals in a responsible, efficient, and impactful way.
What’s new
| Mar 2025 | DM2 is organizing Midwest Speech and Language Days (MSLD) 2025. See you in Notre Dame! |
| Feb 2025 | Check out our latest paper: QG-SMS: Enhancing Test Item Analysis via Student Modeling and Simulation |
| Sep 2024 | Our paper Reference-based Metrics Disprove Themselves in Question Generation has been accepted to EMNLP 2024 Findings. See you in Miami! |
Publications
QG-SMS: Enhancing Test Item Analysis via Student Modeling and Simulation
Authors: Bang Nguyen, Tingting Du, Mengxia Yu, Lawrence Angrave, Meng Jiang
Many tools generate quiz questions, but don’t check if they’re actually good for learning. This paper introduces a new way to test question quality using simulated students, improving how we evaluate educational questions.
Reference-based Metrics Disprove Themselves in Question Generation
Authors: Bang Nguyen, Mengxia Yu, Yun Huang, Meng Jiang
A new reference written by humans can be more different from the original reference than the generated text! You need a better metric and we have it.
Embedding Mental Health Discourse for Community Recommendation
Authors: Hy Dang*, Bang Nguyen*, Noah Ziems, Meng Jiang
People seek support online—but with so many communities, where do they go? We model both how people communicate within a community (via discourse embeddings) and what communities similar users prefer (via collaborative filtering). Our system combines both to recommend the right mental health space for each user.