About Me
Hi 👋, I am Yuan Tian. I'm currently a Ph.D. candidate in the Department of Computer Science at Purdue University, advised by Professor Tianyi Zhang.
My research spans machine learning, natural language processing, and human-computer interaction.
During my PhD, I'm applying grounding
theory and anchoring
effect to make generative AI more controllable and accurate, with a particular focus on
code generation __
I'm broadly interested in advancing AI across all dimensions, such as designing effective architecture &
reasoning pipeline, creating high-quality training & evaluation data, or soliciting human feedback via
efficient interaction design.
My ultimate objective is to increase the earth intelligence (humanity + machine) as a whole.
Publications
EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution
Tianshu Zhang, Kun Qian, Siddhartha Sahai, Yuan Tian, Shaddy Garg, Huan Sun, Yunyao Li
Proceedings of International Conference on Very Large Data Bases
Selective Prompt Anchoring for Code Generation
Yuan Tian, Tianyi Zhang
Proceedings of International Conference on Machine Learning
HuggingFace
Insights into Natural Language Database Query Errors: From Attention Misalignment to User Handling Strategies
Zheng Ning*, Yuan Tian*, Zheng Zhang, Tianyi Zhang, Toby Jia-Jun Li
* Equal Contribution
ACM Transactions on Interactive Intelligent Systems
Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations
Yuan Tian, Zheng Zhang, Zheng Ning, Toby Jia-Jun Li, Jonathan K. Kummerfeld, Tianyi Zhang
Proceedings of Conference on Empirical Methods in Natural Language Processing
An Empirical Study of Model Errors and User Error Discovery and Repair Strategies in Natural Language Database Queries
Zheng Ning*, Zheng Zhang*, Tianyi Sun, Yuan Tian, Tianyi Zhang, and Toby Jia-Jun Li
Proceedings of ACM Conference on Intelligent User Interfaces
Preprints
Supporting Construction Worker Well-Being with a Multi-Agent Conversational AI System
Fan Yang, Yuan Tian, Jiansong Zhang
Preprint
Encountered-Type Haptic Display via Tracking Calibrated Robot
Chenxi Xiao*, Yuan Tian*
* Equal Contribution
Preprint
