Yang Xiao

Yang Xiao

Ph.D. Student @ The Hong Kong Polytechnic University (PolyU)
Intern @ SII
📧 yangxiaocq12@gmail.com 📧 yang-alan.xiao@connect.polyu.hk
🎓 Google Scholar 🚀 Github 🤗 Hugging Face
🐦 Twitter 📚 小红书

I am a Ph.D. Student & Research Assistant at the Department of Computing and Institute of Data Science, at PolyU. I am supervised by Prof. Wenjie Li, with the focus on Large Language Models, LLM Agents.

My short-term research goals focus on LLM reasoning and AI for mathematics, developing more sophisticated reasoning capabilities and mathematical problem-solving systems. My long-term vision is to push the boundaries of machine intelligence, working towards breakthroughs that can fundamentally advance artificial intelligence and its applications for human benefit.

👨💻✨ Our Research Works are Open-Sourced – Explore Them on my GitHub, and our lab 🚀

🏆 Research Achievements:

PolyU Presidential PhD Fellowship, PolyU 2023
Outstanding Demo Paper Award, ACL 2022: DataLab: A Platform for Data Analysis and Intervention
Best Demo Paper Award, ACL 2021: ExplainaBoard: An Explainable Leaderboard for NLP
National Scholarship, Fudan University 2019

Research Work Highlights:

Google Scholar Citation 383, h-index 7, i-10 index 7

🔥 Key Research Contributions:

🚀 Reasoning & Test-time Scaling: LIMO, LIMOPro

🚀 Data Analysis & Evaluation Platforms: DataLab (🏆 Outstanding Demo Award), ExplainaBoard (🏆 Best Demo Award)

Open-Source Research Projects:

First Author Publications:

LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling
Yang Xiao, J Wang, R Yuan, C Xu, K Xu, W Li, P Liu
paper code (2 citations, arXiv 2025)
Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States
Yang Xiao, J Wang, Q Xu, C Song, C Xu, Y Cheng, W Li, P Liu
paper code (ACL 2025)
How far are llms from believable ai? a benchmark for evaluating the believability of human behavior simulation
Yang Xiao, Y Cheng, J Fu, J Wang, W Li, P Liu
paper code (20 citations, arXiv 2023)
DataLab: A Platform for Data Analysis and Intervention
Yang Xiao, Jinlan Fu, Weizhe Yuan, Vijay Viswanathan, Zhoumianze Liu, Yixin Liu, Graham Neubig, Pengfei Liu
paper code 🏆 Outstanding Demo Award (16 citations, ACL 2022)
Are All the Datasets in Benchmark Necessary? A Pilot Study
Yang Xiao, Jinlan Fu, See-Kiong Ng, Pengfei Liu
paper (2 citations, NAACL 2022)

Collaborative Publications:

LIMO: Less is more for reasoning
Y Ye, Z Huang, Yang Xiao, E Chern, S Xia, P Liu
paper code (181 citations, COLM 2025)
Aime-preview: A rigorous and immediate evaluation framework for advanced mathematical reasoning
Y Ye, Yang Xiao, T Mi, P Liu
paper code (7 citations, 2025)
Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
J Wang, K Song, C Xu, C Song, Yang Xiao, D Li, L Qiu, W Li
paper (arXiv 2025)
Olympicarena: Benchmarking multi-discipline cognitive reasoning for superintelligent ai
Z Huang, Z Wang, S Xia, X Li, H Zhou, R Xu, RZ Fan, L Ye, E Chern, Y Ye, Yang Xiao, et al.
paper code (43 citations, NeurIPS 2024)
Towards a client-centered assessment of llm therapists by client simulation
J Wang, Yang Xiao, Y Li, C Song, C Xu, C Tan, W Li
paper code (19 citations, arXiv 2024)
On the Robustness of Reading Comprehension Models to Entity Renaming
Jun Yan, Yang Xiao, Sagnik Mukherjee, Bill Yuchen Lin, Robin Jia, Xiang Ren
paper code (18 citations, NAACL 2022)
ExplainaBoard: An Explainable Leaderboard for NLP
Pengfei Liu, Jinlan Fu, Yang Xiao, Weizhe Yuan, Shuaicheng Chang, et al.
paper code 🏆 Best Demo Award (75 citations, ACL 2021)

📚 Academic Service

Conference Reviewer:

ACL (Association for Computational Linguistics) - Reviewer
EMNLP (Empirical Methods in Natural Language Processing) - Reviewer
NeurIPS (Neural Information Processing Systems) - Reviewer
ICLR (International Conference on Learning Representations) - Reviewer