Research
MerryQuery is a research platform as much as a product. These papers describe the system, how students used it in class, and how teachers helped shape what it became.
Benyamin Tabarsi, Sam Gilson, Faaz Mohamed, Susanna Quayle, Nicole Ackerman-Lowery, Aditya Basarkar, Daniel Briceno, Matheus Marques, Lokesh Sharma, Xiaoyi Tian, Joey Huang, Dongkuan Xu, Tiffany Barnes
How nine K–12 teachers and five undergraduate developers carried classroom concerns into five working tools on MerryQuery.
Benyamin Tabarsi
Proceedings of the 57th ACM Technical Symposium on Computer Science Education V. 2 (SIGCSE TS 2026), pp. 1685–1686
A semester-long study of how students used and perceived MerryQuery in a large introductory course.
Benyamin Tabarsi, Aditya Basarkar, Xukun Liu, Dongkuan (DK) Xu, Tiffany Barnes
Proceedings of the AAAI Conference on Artificial Intelligence, 39(28), pp. 29700–29702
The original MerryQuery system: course-grounded retrieval, cited answers, guided dialogue, and instructor-controlled response granularity.
Benyamin Tabarsi
Proceedings of the AAAI Conference on Artificial Intelligence, 39(28), pp. 29301–29302
From the team, on LLM tools in computing education.
Sam Gilson, Benyamin Tabarsi, Tiffany Barnes
Proceedings of the 27th International Conference on Artificial Intelligence in Education (AIED 2026), Part V, pp. 440–449
Sam Gilson's study on how adversarially perturbed assignments affect the way students seek help from a generative AI chatbot.
Benyamin Tabarsi, Tahreem Yasir, Heidi Reichert, Xiaoyi Tian, Shiva Gadireddy, Clara DiMarco, Daniel Briceno, Lina Battestilli, Tiffany Barnes
Under review at Computers and Education: Artificial Intelligence
A review of 52 studies of student-facing LLM tools in computing education.
Benyamin Tabarsi, Michelle Jiang, Susanna Quayle, et al.
In preparation
HelpLens: an eight-dimension framework comparing teaching-staff and LLM responses to 172 authentic programming questions.
