Wei Xu

phonetic pronunciation: way shoo

Associate Professor
College of Computing & Machine Learning Center
Georgia Institute of Technology

Wei Xu

I am an Associate Professor in the College of Computing (School of Interactive Computing) and the Machine Learning Center at Georgia Institute of Technology. My research focuses on natural language processing, machine learning, and large language models, with interests in multilingual and cross-cultural LLMs, reinforcement learning and post-training, reasoning, long-context and interactive evaluation, and interdisciplinary AI applications.

My group studies how to build language technologies that are robust, useful, and accessible across languages, cultures, domains, and users. Our research is supported by NSF, NIH, DARPA, IARPA, Google, Sony, and other sponsors.

multilingual NLP · LLM reasoning · evaluation · user simulation · interdisciplinary AI+X research

I typically recruit one or two new Ph.D. students each year, along with several research-oriented M.S. students and motivated undergraduates. My lab also host visiting students and research interns. If you apply to Georgia Tech and are interested in working with me, feel free to reach out.

Research

We work on language models, evaluation, and AI systems that interact with people and complex real-world information.

News

Selected Publications

Learning to Route Languages for Multilingual Preference Optimization
Geyang Guo, Hiromi Wakaki, Yuki Mitsufuji, Alan Ritter, Wei Xu
ICML 2026
Flipping the Dialogue: Training and Evaluating User Language Models
Tarek Naous, Philippe Laban, Wei Xu, Jennifer Neville
ICLR 2026
Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?
Ruixin Yang, Ethan Mendes, Arthur Wang, James Hays, Sauvik Das, Wei Xu, Alan Ritter
ICLR 2026
Supporting Informed Self-Disclosure: Design Principles for Presenting AI-Estimates of Privacy Risks to Users
Isadora Krsek, Meryl Ye, Wei Xu, Alan Ritter, Laura Dabbish, Sauvik Das
CHI 2026
GeoRC: A Benchmark for Geolocation Reasoning Chains
Mohit Talreja, Joshua Diao, Jim Thannikary James, Radu Casapu, Tejas Santanam, Ethan Mendes, Alan Ritter, Wei Xu, James Hays
ACL 2026
Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
Jungsoo Park, Hyungjoo Chae, Ethan Mendes, Jay DeYoung, Varsha Kishore, Wei Xu, Alan Ritter
arXiv preprint 2026
Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages
Tarek Naous, Anagha Savit, Carlos Rafael Catalan, Geyang Guo, Jaehyeok Lee, Kyungdon Lee, Lheane Marie Dizon, Mengyu Ye, Neel Kothari, Sahajpreet Singh, Sarah Masud, Tanish Patwa, Trung Thanh Tran, Zohaib Khan, Alan Ritter, Tanmoy Chakraborty, Yuki Arase, Keisuke Sakaguchi, JinYeong Bak, Wei Xu
arXiv preprint 2026
BRANCH: Probabilistic Reasoning with LLMs for Privacy Risk Estimation
Jonathan Zheng, Sauvik Das, Alan Ritter, Wei Xu
NeurIPS 2025
CARE: Multilingual Human Preference Learning for Cultural Awareness
Geyang Guo, Tarek Naous, Hiromi Wakaki, Yukiko Nishimura, Yuki Mitsufuji, Alan Ritter, Wei Xu
EMNLP 2025
SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?
Yao Dou, Michel Galley, Baolin Peng, Chris Kedzie, Weixin Cai, Alan Ritter, Chris Quirk, Wei Xu, Jianfeng Gao
EMNLP 2025
Full publication list
What are Foundation Models Cooking in the Post-Soviet World?
Anton Lavrouk, Tarek Naous, Alan Ritter, Wei Xu
EMNLP 2025
Beyond the Reported Cutoff: Where Large Language Models Fall Short on Financial Knowledge
Agam Shah, Liqin Ye, Sebastian Jaskowski, Wei Xu, Sudheer Chava
COLM 2025
Evaluating LLMs on Chinese Idiom Translation
Cai Yang, Yao Dou, David Heineman, Xiaofeng Wu, Wei Xu
COLM 2025
The Impact of Visual Information in Chinese Characters
Xiaofeng Wu, Karl Stratos, Wei Xu
NAACL 2025
Generating CAD Code with Vision-Language Models for 3D Designs
Kamel Alrashedy, Pradyumna Tambwekar, Zulfiqar Zaidi, Megan Langwasser, Wei Xu, Matthew Gombolay
ICLR 2025
Measuring, Modeling, and Helping People Account for Privacy Risks in Online Self-Disclosures with AI
Isadora Krsek, Anubha Kabra, Yao Dou, Tarek Naous, Laura Dabbish, Alan Ritter, Wei Xu, Sauvik Das
CSCW 2025
CROSSNEWS: A Cross-Genre Authorship Verification and Attribution Benchmark
Marcus Ma, Duong Minh Le, Junmo Kang, Yao Dou, John Cadigan, Dayne Freitag, Alan Ritter, Wei Xu
AAAI 2025
Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges
Xiaofeng Wu, Alan Ritter, Wei Xu
arXiv preprint 2025
Having Beer after Prayer? Measuring Cultural Bias in Large Language Models
Tarek Naous, Michael J. Ryan, Alan Ritter, Wei Xu
ACL 2024 · 🏆 Best Social Impact Award
Reducing Privacy Risks in Online Self-Disclosures with Language Models
Yao Dou, Isadora Krsek, Tarek Naous, Anubha Kabra, Sauvik Das, Alan Ritter, Wei Xu
ACL 2024
FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence
Sebastian Antony Joseph, Lily Chen, Jan Trienes, Hannah Louisa Göke, Monika Coers, Wei Xu, Byron Wallace, Junyi Jessy Li
ACL 2024
InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification
Jan Trienes, Sebastian Joseph, Jörg Schlötterer, Christin Seifert, Kyle Lo, Wei Xu, Byron C. Wallace, Junyi Jessy Li
ACL 2024
Automatic and Human-AI Interactive Text Generation
Yao Dou, Philippe Laban, Claire Gardent, Wei Xu
ACL 2024 Tutorial
Constrained Decoding for Cross-lingual Label Projection
Duong Minh Le, Yang Chen, Alan Ritter, Wei Xu
ICLR 2024
Granular Privacy Control for Geolocation with Vision Language Models
Ethan Mendes, Yang Chen, James Hays, Sauvik Das, Wei Xu, Alan Ritter
EMNLP 2024
ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment
Tarek Naous, Michael J. Ryan, Anton Lavrouk, Mohit Chandra, Wei Xu
EMNLP 2024
Improving Minimum Bayes Risk Decoding with Multi-Prompt
David Heineman, Yao Dou, Wei Xu
EMNLP 2024
ChatHF: Collecting Rich Human Feedback from Real-time Conversations
Andrew Li, Zhenduo Wang, Ethan Mendes, Duong Minh Le, Wei Xu, Alan Ritter
EMNLP 2024 Demo

A more complete and up-to-date publication list is available on Google Scholar and DBLP.

Students

Lab kayaking outing Lab dinner Lab gathering

Group photos with Alan Ritter's lab.

Alumni: Chao Jiang (Ph.D. '25, Apple), Yang Chen (Ph.D. '23, NVIDIA), Mounica Maddela (Ph.D. '23, Bloomberg), Wuwei Lan (Ph.D. '21, Meta), Julie Young (M.S. '26, Microsoft), Xiaofeng Wu (M.S. '25, Baidu), Marcus Ma (M.S. '24, PhD student at USC), Anton Lavrouk (M.S. '24, IMC Trading), David Heineman (B.S. '24, PhD student at Stanford · CoC Outstanding Undergrad Research Award), Jonathan Zheng (B.S. '23, PhD student at Georgia Tech), Michael Ryan (B.S. '23, PhD student at Stanford), Zirui Shao (visiting PhD student from Zhejiang University '25)

Teaching

Service & Awards

Program Co-Chair for EMNLP (2027). Senior Area Chair for ACL, EMNLP, NAACL, and related conferences. Executive Board Member of NAACL (2023–2024). Best Paper Award Committee for ACL (2026) and EMNLP (2024, 2022). Co-organizer of workshops on text generation, evaluation, and user-centered NLP.

Sony Faculty Innovation Award (2026) · ACL Best Social Impact Paper Award (2024) · Google Academic Research Award (2024) · NSF CAREER Award (2022)

Miscellaneous

When I have spare time, I enjoy visiting art museums, attending live performances, hiking, biking, and snowboarding.

Back in 2017, I wrote a biography of my Ph.D. advisor Ralph Grishman along with some early history of Information Extraction research. Ralph was named an ACL Fellow and later received the ACL Lifetime Achievement Award in 2024.