Kevin Sun

My name is Kun (Kevin) Sun. I am currently working at the Department of Linguistics (the Group of Quantitative Linguistics) in the University of Tübingen, Germany. I am also an adjunct professorial research fellow at Fudan University, China. I once worked as associate professor at two Chinese universities.

My research interests include computational linguistics, deep learning, machine learning, computational cognition, and digital humanities. I've conducted extensive research in these areas using computational and experimental techniques. Proficient in Python, R, Java, and Linux Shell, I adeptly employ these languages for text processing, data extraction and analysis, and computational modeling. Skilled in machine learning, statistical analysis, and data mining, I have successfully completed numerous projects employing these methodologies. My primary focus lies in fine-tuning and optimizing Large Language Models (LLMs), as well as evaluating their performance. The overarching objective of my research is to deepen our understanding of how humans and machines process sentences and discourse.

In the field of computational linguistics, I am actively engaged in developing probabilistic multilingual discourse parsers using LLMs. Additionally, I am involved in constructing diverse databases and corpora. Leveraging open-source LLMs, I am creating applications for personality detection, healthcare education, and sports prediction. Furthermore, I am pioneering the synthesis of automatic linguistic analysis. My research also delves into syntax, pragmatics, and discourse using both computational and experimental approaches.

I've gained recognition in the academic community through independent publication in reputable journals and successful applications for competitive research grants. Additionally, I've developed databases, fine-tuned LLM, toolkits, and corpora available for public use in research repositories.

My Email: kun.sun (at) uni-tuebingen.de

My personal information is seen in my CV