Sharing our work at Festival of Learning 2026 in Seoul gave VIABLE Lab plenty to celebrate: five AIED main-track papers and an EDM poster, new conversations with colleagues, and a personal milestone we were happy to share as a team. Seeing this work reach a wider community was rewarding. So was having time together with the people who helped make it possible.
Dr. Anthony F. Botelho, Shan Zhang, Natalia S. Martin, and Hongming (Chip) Li represented the lab in Seoul. The work they brought reflected a much larger team. Zhongtian Huang and Dr. Huan (Hailey) Kuang contributed as co-authors of the AIED full papers, alongside collaborators across institutions. Seiyon M. Lee could not join us, and we missed having her there. We are grateful to everyone whose ideas, effort, and support were part of this week, whether or not they could make the trip.
Held at COEX, the Festival brought together Artificial Intelligence in Education (AIED 2026), Educational Data Mining (EDM 2026), and ACM Learning at Scale (L@S 2026). Workshops and tutorials ran June 27–28, followed by the main program June 29–July 3.
Questions That Connect Our Work
The lab's five AIED papers, comprising four full papers and one short paper, approached educational AI from several directions. A shared concern ran through them: how can we understand what these systems are doing, and what their use means for learners?
When should we trust an AI model's judgment? Chip, Hailey, and Anthony examined whether an LLM's confidence in its own answers could support educational dialogue coding. Their study highlights the need to check and calibrate that confidence before relying on it. In another full paper, Anthony, Zhongtian, Natalia, and Dr. Jinnie Shin studied variation in the time students take to complete mathematics assessments. Shan also contributed to an external collaboration exploring small, private language models as teammates in assessment design. These projects address practical questions about how educational AI can be evaluated and used with care.
What does learning with AI feel and look like for students? Shan and collaborators studied how middle school students talked and worked together while developing chatbots, using Ordered Network Analysis to examine patterns in their collaboration. A related short paper explored the relationship between students' beliefs about their abilities and their intentions to persist. Both bring the focus back to students as active participants, with their own ideas, relationships, and expectations.
Looking More Closely at Help
At EDM, Shan and collaborators presented “Would a Short Explanation Immediately Help? Examining Causal Effects of Students' Help-Seeking in Math.” The study used observational data from ASSISTments to estimate how requesting explanations related to performance on the next problem. Compared with answer-only help, explanations showed little average benefit, while students who engaged more deeply with them showed modest benefits. The finding raises a useful question for learning technologies: when help is available, what supports students in making use of it?
The poster offered a chance to explore those questions with colleagues, including WPI collaborators Eamon Worden and Neil Heffernan and Professor Ken Koedinger. These exchanges are a part of conference life we value: time to ask a follow-up question, hear a different interpretation, and think together about where a project might go next.
Growing Together and Contributing to the Community
For Natalia, Seoul marked her first international academic conference, where she presented an accepted workshop poster. We were proud to celebrate that milestone with her. Moments like this matter to us as a lab: having the opportunity to share your work with a new community, and having teammates alongside you as you do.
The week also included work that helped bring the broader community together. Anthony served as an EDM 2026 Program Chair, and Chip served as an EDM 2026 Web Chair, supporting the conference website and online information.
Shan co-organized two full-day workshops on June 28: the 10th Educational Data Mining in Computer Science Education (CSEDM) Workshop and AI Literacy For All: 2nd International Workshop on AI Literacy Education For All. They created opportunities for researchers and practitioners to exchange ideas about computing education and AI literacy across learning settings. We appreciate the care that goes into making these spaces welcoming and useful for others.
Time Together in Seoul
Beyond COEX, there was time for Myeongdong food stalls, walks through Seoul's busy streets, a picnic by the Han River with friends and longtime collaborators from WPI, and an evening of karaoke. Those moments belong in this story, too. Being able to slow down, share a meal, and enjoy each other's company is part of what makes working together meaningful.
We left Seoul grateful for the people who made the week possible and for the chance to celebrate one another's work. The papers capture the research; the memories of this trip also include the friendships and support that help sustain it. To our collaborators, colleagues, and friends who spent time with us: thank you. We look forward to continuing the conversations and welcoming new collaborators along the way.
Presented Work
AIED 2026 - Technical Aspects of AIED, Full Papers
[1] Can We Trust AI's Self-Assessment? Evaluating and Improving LLM Confidence Calibration in Educational Dialogue Coding
Li, H., Kuang, H., & Botelho, A. F. (2026). DOI: 10.1007/978-3-032-29755-6_18 | Detailed project page and talk materials
[2] Small, Private Language Models as Teammates for Educational Assessment Design
Jaldi, C. D., Saini, A., Zhang, S., Schroeder, N., Shimizu, C., & Ilkou, E. (2026). DOI: 10.1007/978-3-032-29755-6_15
External collaboration involving Shan Zhang.
[3] Modeling Completion Time in Mathematics Formative Assessments: Content-Based Prediction of Time Variation
Botelho, A. F., Huang, Z., Martin, N. S., & Shin, J. (2026). DOI: 10.1007/978-3-032-29755-6_21
AIED 2026 - Human Aspects of AIED
[4] Analyzing Middle School Students' Dialogue and Behaviors during Collaborative AI Chatbot Development Using Ordered Network Analysis
Zhang, S., Zambrano, A. F., Tian, X., Song, Y., Botelho, A. F., Boyer, K. E., Israel, M., & Jiang, S. (2026). DOI: 10.1007/978-3-032-29763-1_23
[5] An Attitude Paradox? Examining Ability Beliefs and Persistence Intentions in a Middle School Conversational AI Learning Experience
Tian, X., Zhang, S., Song, Y., McKlin, T., Boyer, K. E., & Israel, M. (2026). DOI: 10.1007/978-3-032-29770-9_57
EDM 2026 - Poster and Demo Track
[6] Would a Short Explanation Immediately Help? Examining Causal Effects of Students' Help-Seeking in Math
Zhang, S., Worden, E., Leite, W., Heffernan, N. T., & Botelho, A. F. (2026). DOI: 10.5281/zenodo.21039683 | EDM proceedings