Wei Xu     

[phonetic pronunciation: way shoo ]

Associate Professor
College of Computing
Georgia Institute of Technology
  wei.xu@cc.gatech.edu
  @cocoweixu

I am a faculty member in Computer Science at Georgia Tech’s School of Interactive Computing (one of four schools in College of Computing) and Machine Learning Center. My research focuses on advancing large language models across three areas: My work has been recognized with the NSF CAREER Award; Faculty Research Awards from Google, Sony, and Criteo; the CrowdFlower AI for Everyone Award; and Paper Awards at COLING’18 and ACL’24. My research lab is supported by grants from NSF, NIH, DARPA, and IARPA. I received my Ph.D. in Computer Science from New York University and my B.S./M.S. from Tsinghua University.

  I plan to recruit 1–2 PhD students for Fall 2026 (please apply to the Machine Learning or CS PhD program and list me as a potential advisor). I also recruit research-oriented MS students (apply to the MSCS program and email me) and motivated undergraduates with sufficient time to commit to research. Although I do not normally respond to admission inquiries given the volume, a brief email after you submit your application can help ensure I don’t miss it in the system.
What's New
Research Highlights

Multilingual Multicultural LLMs

While LLMs have demonstrated impressive performance, their success is largely concentrated in English and other high-resource languages. In contrast, many non-English languages remain underrepresented and underserved. Moreover, these models often reflect Western cultural biases and struggle to capture the nuances of non-Western cultural contexts (Naous et al., ACL 2024; Naous et al., NAACL 2025). We work on identifying and closing these gaps in performance and cultural adaptation. Addressing these challenges calls for a deeper analysis of pre-training data to identify and mitigate representational gaps, as well as alignment (Guo et al., arXiv 2025) and inference-time algorithms (Le at al., ICLR 2024) that can dynamically adapt model behavior to diverse linguistic and cultural contexts.

Robustness and Reasoning of LLMs

Artificial General Intelligence (AGI) benchmarks seek to assess an AI system’s capacity to perform tasks that require human-level intelligence, including reasoning, learning, and adapting to novel situations (Zheng et al., ACL 2024; Mendes et al., EMNLP 2024). While current systems fall short of true AGI, there is growing interest in moving beyond static benchmarks toward more realistic, dynamic evaluations. Our research focuses on designing real-world tasks that better reflect practical challenges faced by LLMs, and on developing innovative methods (Zheng et al., arXiv 2025) to enhance their robustness and performance in these complex settings.

Interdisciplinary NLP+X Research

We actively collaborate with researchers to explore impactful real-world applications of large language models in Human-Computer Interaction, Security and Privacy, Healthcare, and Law (Jiang et al., EMNLP 2024; Dou et al., ACL 2024). As LLMs continue to advance, they offer exciting new capabilities across specialized domains. There are a lot of opportunities, as LLMs often exhibit promising but inconsistent performance in domain-specific tasks, where precision, context sensitivity, and domain knowledge are critical.

NLP X Lab

photos together with Alan Ritter's group














    Yao Dou (CS PhD student; human-centered LLM evaluation, generation)
    Tarek Naous (ECE ML PhD; multilingual multicultural LLM)
    Duong Minh Le (CS PhD; multilingual LLM -- co-advisor: Alan Ritter)
    Jonathan Zheng (ML PhD; reasoning, robustness of LLM -- co-advisor: Alan Ritter)
    Geyang Guo (CS PhD; LLM alignment -- co-advisor: Alan Ritter)
    Junmo Kang (CS PhD; efficiency -- co-advisor: Alan Ritter)
    Usneek Singh (CS MS, autumn 2025 -- )
    Yiren Wang (CS MS, autumn 2025 -- )
    Zicong He (ECE MS, summer 2025 -- )
    Govind Ramesh (BSMS, winter 2022 -- ; LLM safety)
    Jerry Zheng (BSMS, autumn 2025 -- )
    Julie Young (BSMS, autumn 2025 -- )
    Rachel Choi (part-time, summer 2022 -- )
    Oleksandr Lavreniuk (Undergrad, summer 2024 -- )
    Sara Takagi (Undergrad, summer 2025 -- )
    Katerina Addington (Undergrad, autumn 2025 -- )
    Eric Kim (Undergrad, autumn 2025 -- )
    Frank Chang (Undergrad, autumn 2025 -- )
    Guanjun Yan (Undergrad, autumn 2025 -- )
    Alexey Plagov (Undergrad, autumn 2025 -- )
    Benjamin Mamut (Undergrad, autumn 2025 -- )
    Jiayu Liu (Undergrad intern from UIUC, summer 2025 -- )

Alumni (with theses)
    Chao Jiang (PhD 2025 → Apple AI/ML research)
    Yang Chen (PhD 2024, co-advisor: Alan Ritter → Research Scientist at NVIDIA)
    Mounica Maddela (PhD 2023 → Bloomberg AI)
    Wuwei Lan (PhD 2021 → Applied Scientist at Amazon)
    Xiaofeng Wu (MS 2025 → Baidu)
    Marcus Ma (MS 2024 → PhD student at USC)
    Anton Lavrouk (MS 2024 → Lockheed Martin)
    David Heineman (BS 2024, CoC Outstanding Undergrad Research Award → Predoctoral young investigator at AI2)
    Jonathan Zheng (BS 2023 → PhD student at Georgia Tech)
    Michael Ryan (BS 2023 → PhD student at Stanford)

Publications
Teaching
Current Offering:
Previous Offerings:

Service

Miscellaneous

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

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

I also photographed and made a list of the best dressed NLP researchers in 2016/17 , 2015 and 2014.