Bio
Guoliang Xu is a Ph.D. candidate in Applied Statistics at Columbia University. His research bridges statistical modeling, psychometrics, and artificial intelligence, with a focus on large language models (LLMs). He investigates how retrieval-augmented generation (RAG) and causal inference frameworks can be integrated with LLMs to advance automated assessment, enhance model interpretability, and support data-driven decision making.
He is advised by Professor James E. Corter (primary advisor).
He is advised by Professor James E. Corter (primary advisor).
Recent News
[Nov 2025] Received the Helen M. Walker Scholarship from Measurement, Evaluation and Statistics Program,Teachers College, Columbia University.
[Nov 2025] Paper was Accepted to the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26) .
[Oct 2025] Received the Provost’s Grant for Doctoral Research from Teachers College, Columbia University.
[Jul 2025] Paper Extracting Latent Dimensions from Multidimensional Response Timing Data was published in the Proceedings of the 47th Annual Meeting of the Cognitive Science Society (CogSci 2025)
[April 2025] Presented at the National Council on Measurement in Education (NCME) Annual Meeting.
Education
2022–2026 (expected)
Ph.D. in Applied Statistics, Columbia University
Focus: Machine Learning, LLM-RAG, LLM-Causal Inference
Focus: Machine Learning, LLM-RAG, LLM-Causal Inference
2020–2022
M.S. in Applied Statistics, Columbia University
2020
B.A. in Economics and Finance, University of Aberdeen
Publications
Journal Articles
Paper 2 under review
This paper is about the number 3. The number 4 is left for future work.
Paper under review
This paper is about the number 2. The number 3 is left for future work.
Conference Papers
Teaching
Teaching Assistant
HUDM 5059: Psychological measurement, Teachers College, Columbia University, 2025
Teaching Assistant
HUDM 4120: Introduction to Statistics, Teachers College, Columbia University, 2024
Teaching Assistant
HUDM 5123: Linear Models Experimentl Dsgn, Teachers College, Columbia University, 2024
Teaching Assistant
HUDM 6055: Latent Structure Analysis, Teachers College, Columbia University, 2022
CV
View Full CV →Research experience
Spring 2025 — Present: Graduate Research Assistant
- Institution: Teachers College, Columbia University
- Project: Education Leadership Data Analytics (ELDA)
- Research Focus: Conducted correspondence analysis on a large-scale dataset of state education records aligned with 16 NASEM equity indicators to uncover latent dimensions of equity representation across states.
Fall 2024 — Present: Ph.D. Researcher
- Institution: Columbia University, New York, NY
- Project: LLM-RAG for Automated Grading
- Research Focus: Developed a retrieval-augmented generation (RAG) framework for automated short-answer grading and feedback, integrating LLMs with psychometric and causal inference principles.
Jan 2023 — Jun 2024: Research Assistant
- Institution: Columbia University, New York, NY
- Project: NSF-Funded Course Recommendation-Causal Inference
- Research Focus: Processed large-scale NCES datasets to model student math course pathways across grade levels. Applied causal machine learning methods (TMLE, Causal Forests) to estimate heterogeneous intervention effects and design optimal course recommendation rules that promote fairness and maximize student outcomes.
Jan 2021 — Feb 2022: Master’s Researcher
- Institution: Columbia University
- Project: Machine and Deep Learning Research
- Research Focus: Built predictive models for crime data using principal component regression and model selection, improving predictive accuracy from 55% to 90%. Developed NLP pipelines for sentiment analysis and topic modeling, and analyzed classroom interaction networks using centrality and community measures to examine peer influence and group dynamics.
Skills
- Tools
- Python
- R
- SQL
- SPSS
- Machine Learning & AI
- Machine Learning
- LLM-RAG
- LLM-Causal Inference
Service and leadership
- Reviewer, Cognitive Science Society Annual Meeting (CogSci 2025)
- Reviewer, AAAI Undergraduate Consortium (AAAI-UC 2026)
Award
- Doctoral Fellowship (2023)
- Provost’s Grant (2025)
- Helen M. Walker Scholarship (2025)
Courses
Machine Learning (Stanford Online)
Published:
Advanced seminar exploring supervised learning,unsupervised learning,learning theory,reinforcement learning.
Applied Causal Inference for Data Science
Published:
This is an introductory and applied course in Casual Inference .