Xiaohan Xu

Bio

I am currently a second-year student at The University of Hong Kong pursuing a Ph.D. in Computer Science, advised by Prof. Reynold Cheng. I am a member of HKU BIRD Team focusing on AI for Databases and text-to-SQL.

Before that, I received my M.S. from Institute of Information Engineering, Chinese Academy of Sciences, advised by Prof. Hongbo Xu. I earned my B.S. in Automation from Beijing Institute of Technology, supervised by Prof.Yuan Li. During my undergraduate study, I had an opportunity to participate in a summer research program on data mining at the Illinois Institute of Technology, mentored by Dr. Zelenberg. Additionally, I gained valuable industry and research institute experience through internships at Microsoft, Baidu Inc., and Beijing Academy of Artificial Intelligence (BAAI), etc. In addition, I feel grateful and honored to collaborate on multiple research projects with Google Cloud on text-to-SQL.

My research interests focus on Large Language Model with structured data, e.g. Database, Knowledge Graph (KG), etc..

News⭐️

2025-06-09: ⭐️ We released the BIRD-Interact, another collaboration with Google Cloud. This project focuses on evaluating the dynamic interaction ability of LLM Agents with both Database environment and User to finish the text-to-SQL tasks. Paper.
2025-06-28: ⭐️ We released the BIRD-CRITIC, a collaboration with Google Cloud. This project focuses on the research question "Can Large Language Models Solve USER SQL Issues in Real-World Database Applications?". Paper is accepted by NeurIPS 2025!
2025-05-30: ⭐️ We released LiveSQLBench, a contamination-free, continuously updating benchmark (like LiveBench) designed to evaluate LLMs on complex, real-world text-to-SQL tasks.
2024-09-22: ⭐️ Two papers are accepted by EMNLP 2024: Rereading for LLM's reasoning, Survey of LLM-as-Evaluator.

Publications

^‡ indicates equal contribution.

Selected
All

BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions

Nan Huo^‡, Xiaohan Xu^‡, Jinyang Li^‡, Per Jacobsson, Shipei Lin, Bowen Qin, Binyuan Hui, Xiaolong Li, Ge Qu, Shuzheng Si, Linheng Han, Edward Alexander, Xintong Zhu, Rui Qin, Ruihan Yu, Yiyao Jin, Feige Zhou, Weihao Zhong, Yun Chen, Hongyu Liu, Chenhao Ma, Fatma Ozcan, Yannis Papakonstantinou, Reynold Cheng

Arxiv 2025

Paper Code

SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

Jinyang Li, Xiaolong Li, Ge Qu, Per Jacobsson, Bowen Qin, Binyuan Hui, Shuzheng Si, Nan Huo, Xiaohan Xu, Yue Zhang, Ziwei Tang, Yuanshuai Li, Florensia Widjaja, Xintong Zhu, Feige Zhou, Yongfeng Huang, Yannis Papakonstantinou, Fatma Ozcan, Chenhao Ma, Reynold Cheng

NeurIPS 2025

Paper Code

A survey on knowledge distillation of large language models

Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, Tianyi Zhou

Arxiv 2024

Paper Code

Leveraging large language models for nlg evaluation: A survey

Zhen Li^‡, Xiaohan Xu^‡, Tao Shen, Can Xu, Jia-Chen Gu, Chongyang Tao

EMNLP 2024

Paper Code

Re-reading improves reasoning in language models

Xiaohan Xu, Chongyang Tao, Tao Shen, Can Xu, Hongbo Xu, Guodong Long, Jian-guang Lou, Shuai Ma

EMNLP 2024

Paper Code

Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs

Xiaohan Xu, Peng Zhang, Yongquan He, Chengpeng Chao, Chaoyang Yan

IJCAI'22 Long Presentation

Paper Code

BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions

Arxiv 2025

Paper Code

SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

NeurIPS 2025

Paper Code

A survey on knowledge distillation of large language models

Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, Tianyi Zhou

Arxiv 2024

Paper Code

Leveraging large language models for nlg evaluation: A survey

Zhen Li^‡, Xiaohan Xu^‡, Tao Shen, Can Xu, Jia-Chen Gu, Chongyang Tao

EMNLP 2024

Paper Code

Re-reading improves reasoning in language models

Xiaohan Xu, Chongyang Tao, Tao Shen, Can Xu, Hongbo Xu, Guodong Long, Jian-guang Lou, Shuai Ma

EMNLP 2024

Paper Code

MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge Distillation

Longzheng Wang^‡, Xiaohan Xu^‡, Lei Zhang, Jiarui Lu, Yongxiu Xu, Hongbo Xu, Chuang Zhang

Arxiv 2024

Paper

Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs

Xiaohan Xu, Peng Zhang, Yongquan He, Chengpeng Chao, Chaoyang Yan

IJCAI'22 Long Presentation

Paper Code

Cross-modal Contrastive Learning for Multimodal Fake News Detection

Longzheng Wang, Chuang Zhang, Hongbo Xu, Yongxiu Xu, Xiaohan Xu, Siqi Wang

ACMMM 2023

PoKE: Prior Knowledge Enhanced Emotional Support Conversation with Latent Variable

Xiaohan Xu, Xuying Meng, Yequan Wang

Preprint 2023

Paper

Vitæ

Full Resume in PDF.

The University of Hong Kong Sep 2024 - now

Ph.D.
Computer Science, NLP
UCAS, IIE Sep 2021 - Jun 2024

M.S.
Cyberspace Security, NLP
Microsoft May 2023 - now

Research Intern
Large Language Model
Baidu Inc. Nov 2022 - May 2023

Research Intern
XiaoDu Cloud, NLP
BAAI Apr 2022 - Oct 2022

Research Intern
Foundation Model, NLP
Shenzhen Qianan Inc. Jul 2021 - Sep 2021

Research Intern
Big Data Group, ML
Illinois Institute of Technology Jul 2019 - Sep 2019

Summer Research
Data Mining
University of Alberta Jul 2018 - Aug 2018

Exchange Student
School-sponsored exchange program
Beijing Institute of Technology Sep 2017 - Jun 2021

B.Sc. Student
Automation
National Scholarship
National Encouragement Scholarship

Awards

Postgraduate Scholarship (PGS) , HKU, 2024
National Scholarship (<2%), Beijing Institute of Technology, 2018
National Encouragement Scholarship (<5%), Beijing Institute of Technology, 2019
Excellent Student Model (<2%), Beijing Institute of Technology, 2018

Acknowledgement

Thanks to Martin Saveski for the website template.