I am currently visiting SALT Lab and Stanford NLP Group! I am pursuing my PhD in Computer Science at the National University of Singapore (NUS) WING lab with research interests in human-centered and socially aware Natural Language Processing. I am fortunately supervised by Prof Kan Min-Yen from NUS, Dr Nancy F. Chen from ASTAR, and Prof Shafiq Joty from Salesforce. I am also having great collaborations with SALT Lab under the advice of Prof Diyi Yang from Stanford University. I graduated with a bachelor in NUS.

My research interests include (1) Human-Centric and Data-Centric NLP, (2) NLP for Social Good and ๏ผˆ3๏ผ‰Socially Aware NLP System. I have published papers at the top tier NLP conferences like ACL and EMNLP.

I like playing piano๐ŸŽน, table tennis๐Ÿ“ and badminton๐Ÿธ. I enjoy listening to music and watching talk shows because they deliver inspiration and positive energy through words and rhythms. I also like traveling and exploring the world/good food!๐Ÿ˜‹ I am learning golf recentlyโ›ณ๏ธ

๐Ÿ”ฅ News

  • 2024.11: ย ๐ŸŽ‰๐ŸŽ‰ I received Google PhD Fellowship (NLP direction)!
  • 2024.09: ย ๐ŸŽ‰๐ŸŽ‰ I started my visit at Stanford!
  • 2024.05: ย ๐ŸŽ‰๐ŸŽ‰ Our paper (as first author) Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future was accepted by ACL 2024 Findings.
  • 2024.01: ย ๐ŸŽ‰๐ŸŽ‰ I received Research Achievement Award awarded by School of Computing!
  • 2023.12: ย ๐ŸŽ‰๐ŸŽ‰ I passed my PhD Qualification Exam!
  • 2023.10: ย ๐ŸŽ‰๐ŸŽ‰ Our paper (as first author) CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation was accepted by EMNLP 2023 Main Conference.
  • 2023.10: ย ๐ŸŽ‰๐ŸŽ‰ Our paper (as collaborator) Retrieving Multimodal Information for Augmented Generation: A Survey was accepted by EMNLP 2023 Findings.
  • 2022.03: ย ๐ŸŽ‰๐ŸŽ‰ Our paper (as first co-author) Inducing Positive Perspectives with Text Reframing was accepted by ACL 2022 Main Conference. We also received Outstanding Paper Award!

๐Ÿ“ Publications

๐ŸŽ™ First (Co-)Author

2023
sym

(2) Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future

Minzhi Li, Weiyan Shi, Caleb Ziems, Diyi Yang

ACL 2024

  • We build a Social AI Data Infrastructure, which consists of a comprehensive social AI taxonomy and a data library of 480 NLP datasets. Our infrastructure allows us to analyze existing dataset efforts, and also evaluate language modelsโ€™ performance in different social intelligence aspects. Our analyses demonstrate its utility in enabling a thorough understanding of current data landscape and providing a holistic perspective on potential directions for future dataset development.
2023
sym

(2) CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation

Minzhi Li, Taiwei Shi, Caleb Ziems, Min-Yen Kan, Nancy F. Chen, Zhengyuan Liu, Diyi Yang,*

EMNLP 2023

  • This work propose CoAnnotating, a novel paradigm for Human-LLM co-annotation of unstructured texts at scale. Under this framework, we utilize uncertainty to estimate LLMsโ€™ annotation capability. Our empirical study shows CoAnnotating to be an effective means to allocate work from results on different datasets, with up to 21% performance improvement over random baseline.
2023
sym

(1) Inducing Positive Perspectives with Text Reframing

Caleb Ziems, Minzhi Li (equal contribution), Anthony Zhang, Diyi Yang

ACL 2022

  • We introduce a large-scale benchmark, Positive Psychology Frames, with 8,349 sentence pairs and 12,755 structured annotations to explain positive reframing in terms of six theoretically-motivated reframing strategies. Then we evaluate a set of state-of-the-art text style transfer models, and conclude by discussing key challenges and directions for future work.

๐ŸŽ™ Co-author

  • (1) Ruochen Zhao, Hailin Chen, Weishi Wang, Fangkai Jiao, Xuan Long Do, Chengwei Qin, Bosheng Ding, Xiaobao Guo, Minzhi Li, Xingxuan Li, Shafiq Joty, 2023. Retrieving Multimodal Information for Augmented Generation: A Survey. EMNLP Findings (2023): 2207397. link

๐ŸŽ– Honors and Awards

  • 2024.11 Google PhD Fellowship (NLP Direction)
  • 2024.01 Research Achievement Award
  • 2022.08 ACIS Scholarship Award
  • 2022.01 21/22 S1 Deanโ€™s List Award
  • 2021.01 20/21 S1 Deanโ€™s List Award
  • 2018.08 Science and Technology Merit Scholarship
  • 2013.11 MOE SM1 Scholarship

๐Ÿ“– Educations

  • 2024.09 - 2025.09, Visiting Ph.D., Department of Computer Science, Stanford University
  • 2022.08 - Present, Ph.D., Department of Computer Science, School of Computing, National University of Singapore, Singapore
  • 2018.08 - 2022.05, B.S., Business Analytics, School of Computing, National University of Singapore, Singapore
  • 2014.01 - 2017.11, Dunman High School, Singapore.
  • 2010.08 - 2013.05, Nanjing Foreign Language School, Nanjing, China.

๐Ÿ’ฌ Research Interest

  • (1) Human-Centric and Data-Centric NLP
  • (2) NLP for Social Good
  • (3) Socially Aware NLP System