BIRD-Interact project: Focusing on evaluating the dynamic interaction ability of LLM Agents with both Database environment and User to finish the text-to-SQL tasks, paper released
BIRD-CRITIC project: Research question on whether Large Language Models can solve USER SQL issues in real-world database applications, paper accepted by NeurIPS 2025
LiveSQLBench project: A contamination-free, continuously updating benchmark designed to evaluate LLMs on complex, real-world text-to-SQL tasks
Two papers accepted by EMNLP 2024: 'Rereading for LLM's reasoning' and 'Survey of LLM-as-Evaluator'
Published multiple papers including 'BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions', 'SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications', 'A survey on knowledge distillation of large language models', etc.
Background
Research Interests: Large Language Model with structured data, e.g., Database, Knowledge Graph (KG), etc. Professional Field: Computer Science. Bio: Currently a second-year Ph.D. student in Computer Science at The University of Hong Kong, advised by Prof. Reynold Cheng. He is a member of the HKU BIRD Team, focusing on AI for Databases and text-to-SQL.