After a five-year hiatus, the Deep Dive into Digital and Data Methods for Chinese Studies series (Deep Dive) returns to U-M on Monday, November 16, 2026, with a day of programming featuring Dr. Kwok-leong Tang of Harvard University. Titled “AI in Practice: From Critical Evaluation to Tool Building,” the event will offer three sessions (a workshop, a demonstration, and office hours) to explore artificial intelligence in research and practice in Chinese and East Asian studies.
The revival marks a new chapter for the Deep Dive series that has brought scholars, students, and librarians together to explore the possibilities of digital scholarship in Chinese studies since 2016.
A Decade of Deep Dive
Deep Dive was a lecture and workshop series launched by Liangyu Fu, then Chinese Studies Librarian, and Mary Gallagher, then director of the Lieberthal-Rogel Center for Chinese Studies (LRCCS) in 2016. Co-sponsored by the Asia Library and LRCCS, the series was designed to connect U-M’s Chinese studies community with scholars at the forefront of digital scholarship and data research, and to foster a deeper understanding of how the digital environment could support Chinese studies.
From the beginning, the series combined local expertise with an international outlook. U-M faculty and researchers shared “home-grown” projects alongside scholars from other U.S. institutions. Deep Dive also welcomed scholars and teams from Germany, the Netherlands, Singapore, and Taiwan, recognizing that important digital scholarship projects and tools were being developed around the world.
Ten events took place before the pandemic, attracting an enthusiastic following that extended well beyond Ann Arbor. In response to growing interest, the Asia Library and LRCCS established travel grants in 2019 to help researchers attend. These grants supported 19 scholars from the U.S. and Canada in attending Deep Dive events in Ann Arbor.
The final in-person event before the pandemic took place in February 2020, shortly before pandemic shutdowns began. A Zoom event followed in 2021, after which the series entered a five-year pause amid pandemic-related disruptions and shifting responsibilities, though plans for its return remained on the horizon.
Returning with workshops on AI in practice
Deep Dive now returns to a research landscape increasingly shaped by generative AI. Its opening event, “AI in Practice: From Critical Evaluation to Tool Building,” brings the series’ longstanding interest in digital methods into conversation with this rapidly developing area.
The featured speaker, Dr. Kwok-leong Tang, is Managing Director of the Digital China Initiative and a lecturer in Harvard University’s Department of East Asian Languages and Civilizations. A historian by training, he earned his bachelor’s and master’s degrees in history from the Chinese University of Hong Kong and his Ph.D. in history and Asian Studies from Pennsylvania State University. In recent years, Dr. Tang has focused on exploring the potential of new technologies in humanities research. He has organized and taught workshops on adopting generative AI in Chinese studies and humanities research at Harvard and other institutions.
Please see below for event details. We look forward to welcoming our community back for another deep dive.
Morning workshop: When AI Gets It Wrong — Learning Generative AI Through Its Mistakes
Time: 10 am-11:30 am, Monday, November 16, 2026
In-person at Hatcher Gallery Lab (Room 100H), OR register HERE to attend on Zoom
Generative AI tools often make mistakes, especially with historical East Asian sources. This hands-on workshop uses those mistakes to explain how the technology works, so that participants can decide when to trust it and when to use it. When an AI tool gives a wrong answer, there are two possible reasons: the model itself cannot do the task, or we have not given it what it needs. The workshop teaches how to tell these apart. First, we will run a small AI model on our own laptops and look inside it: how it reads text, how it chooses each word, and why it can sound certain and still be wrong. Next, we will see how clearer instructions, more context, or a connected tool can fix some mistakes but not others. Finally, we will practice a simple way to test an AI answer: ask the same question several times and check the results against a reliable source.
No technical background is needed.
Please note that a laptop is required for in-person participants. The Hatcher Gallery Lab is equipped with laptops, but please feel free to bring your own.
Afternoon demonstration: From Printed Page to Research Data — Building Humanities Tools with AI Agents
Time: 2 pm-3:30 pm, Monday, November 16, 2026
In-person at Hatcher Gallery Lab (Room 100H), OR register HERE to attend on Zoom
This session is a live demonstration. Dr. Tang will show how AI coding agents, such as Claude Code, let a humanist build research tools by describing them in plain language, without being a trained programmer. The main demonstration is a full pipeline that turns printed materials into structured data: scanned pages go through OCR (turning page images into text), and the text then becomes a table of people, places, and dates, each checked against reference databases such as Wikidata and CBDB (China Biographical Database Project). Dr. Tang will also show other tools he has built this way, including a batch OCR tool, a converter for historical Chinese, Japanese, and Korean dates, a tool that suggests Library of Congress subject headings, and classroom history games made from primary sources. Throughout, we will look at how to check the agent's work and where this approach breaks down.
In this session, participants mainly watch and ask questions; no laptop or setup is needed for in-person attendees.
Office Hours with Dr. Tang
Time: 3:45 pm-5:00 pm, Monday, November 16, 2026
In-person only at Hatcher Gallery Lab (Room 100H)
Following the demonstration, Dr. Tang will host an optional office hour for in-person participants who are interested in discussing their own projects related to AI and East Asian studies. This informal session offers an opportunity to receive feedback, explore possible approaches, and consider both the potential and limitations of AI tools for your projects.