AI in Practice: From Critical Evaluation to Tool Building ~ Deep Dive into Digital and Data Methods for Chinese Studies series8.11.2026 {en}
Dr. Kwok-leong Tang, managing director of the Digital China Initiative at Harvard University, will present „AI in Practice: From Critical Evaluation to Tool Building“ on Monday, November 16, 2026, as part of the Deep Dive into Digital and Data Methods for Chinese Studies series. The Deep Dive series is co-sponsored by the University of Michigan’s Asia Library and the Lieberthal-Rogel Center for Chinese Studies.
The full-day program will be held in a hybrid format, with in-person attendance at Hatcher Library in Ann Arbor, Michigan. We welcome participation via Zoom for the following two sessions. Please register using the links below and feel free to share this announcement with anyone who might be interested.
-
When AI Gets It Wrong — Learning Generative AI Through Its Mistakes
Time: 10:00-11:30 am EST, Monday, November 16, 2026
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.
-
Demonstration: From Printed Page to Research Data — Building Humanities Tools with AI Agents
Time: 2:00-3:30 pm EST, Monday, November 16, 2026
Register HERE to attend on Zoom (Please note that this link differs from the one above)
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.
Source: [Workshops] AI in Practice: From Critical Evaluation to Tool Building ~ Deep Dive into Digital and Data Methods for Chinese Studies series ~ University of Michigan, Nov. 16, 2026 ~ Hybrid | H-Net, H-Net: Humanities & Social Sciences Online „CC BY-NC-ND 4.0.“
