Festival of Learning 2026

Workshop papers

PELE | Saturday | Half Day - PM | COEX 321 | sites.google.com/carnegielearning.com/pele-2026 

• Accounting for Classrooms in Online A/B Tests with Student-Level Randomization: The Ordered LOOP Estimator. Yanping Pei, Adam Sales, Johann Gagnon-Bartsch, Eamon Worden and Neil Heffernan | Link to paper

• A Case Study Reexamining the Cold-Start Problem in Knowledge Tracing Models and Implications for SafeInsights, an Education Research Infrastructure. Jiayi Zhang, Ryan S. Baker, Debshila Basu Mallick, Cristina Heffernan & Neil Heffernan | https://arxiv.org/pdf/2606.11004 

iRAISE | Sunday | Full Day | COEX 403 | safeinsights.github.io/iraise26

• Can Large Language Models Understand How Students Learn? Shashank Sonkar (UCF), Eamon Worden (WPI), Neil & Cristina Heffernan (WPI & ASSISTments)| https://arxiv.org/pdf/2602.00070 

• Beyond Aggregate Accuracy: Continuous Evaluation of Residual Failures in Image-Required Educational Mathematics. Ethan Croteau & Neil Heffernan | Link to paper

• More Sources, Better AI? When Context Helps and Harms AI-Assisted Discovery in Educational Data Archives. Xin Wei, Morgan Lee, Jie Min, Jeremy Roschelle

iTextbook | Sunday | Full Day | Multicampus 404

• Representing Image-Required Mathematics for Intelligent Textbooks: A Controlled Comparison of Diagram Encodings. Ethan Croteau & Neil Heffernan | Link to paper

Conference Papers

• L@S | Lim, W.-C., Worden, E., Sales, A., & Heffernan, N. T. (2026). LLM-Generated Summaries for Teachers: A Randomized Field Experiment in a Digital Learning Platform. https://doi.org/10.1145/3774398.3811606 (URL will not be active until June 28, 2026). Session L@S#1 | 6/29 Monday @ 10:45 | Room North 205 | Link to paper

• AIED | Worden, E., Heffernan, C., Heffernan, N., & Sonkar, S. (2026). FoundationalASSIST: Dataset for Foundational Knowledge Tracing & Pedagogical Grounding of Large Language Models. Session AIED19 (TS) | 6/29 Monday @ 14:00 | Room 102 | Link to paper

• L@S | Worden, E., Dang, L., Lim, W.-C., Miller, S., Zhang, J., Haim, A., Sales, A., Gurung, A., & Heffernan, N. (2026). A Large Scale Randomized Control Trial Showing LLM Generated Feedback Helps Low-Knowledge Middle School Math Students with Short-Term Learning. Session L@S#3 | 6/29 Monday @ 15:45 | Room North 205 | Link to paper

• JEDM | Croteau, E. & Heffernan, N. (2026). Seeing Is Solving: MLLMs, Reasoning, and Refusal in Visual Math. Journal of Educational Data Mining, 18(1), 244-285.
  Session EDM09 | 7/1 Wednesday @ 10:45 | North 202 | https://doi.org/10.5281/zenodo.19420820 

• AIED | Worden, E., Lee, M., Siedahmed, A., Sales, A., Zhang, J., Shraga, R., & Heffernan, N.T. (2026). Short, Long, or Affective: Evaluating LLM-Generated Feedback Styles for Student Learning. Session AIED57 (TL) | 7/2 Thursday @10:45 | Aud Meeting 2 | Link to paper