Yushi SUN

I am a final-year PhD candidate at Hong Kong University of Science and Technology (HKUST) majored in Computer Science and Engineering supervised by Prof. Lei CHEN. I am fortunate to work with Prof. Nan TANG and Xin Luna Dong during my PhD journey.

I received the B.S. degree in Computer Science and Applied Mathematics from Hong Kong University of Science and Technology (HKUST) in 2021. More details of me are introduced in my CV.

Email  /  Google Scholar  /  Github  /  Linkedin

My research interest lies in the following database topics: Data Quality (focusing on high-quality data labeling/preparation, which targets the correctness and completeness of data), LLMs, and RAG.
My vision is to synthesize the strengths of data quality (DQ) and LMs fields and conduct research on DQ4LM and LM4DQ. Feel free to drop me an email if you are interested.
Representative papers on DQ and LM are highlighted in yellow and blue respectively.

We constructed a comprehensive RAG benchmark and hosted the KDD Cup competition.

We conducted an extensive evaluation of SOTA LLMs on taxonomies.

We proposed a novel cross-domain-aware worker selection with training approach for crowdsourced data labeling.

We defined a novel named entity schema for related and sub-related table discovery and alignment for enhancing the annotation quality of column semantic types.