Saved in:
Bibliographic Details
Main Authors: Chen, Eason, Judicke, Sophia, Beigh, Kayla, Tang, Xinyi, Xiao, Zimo, Li, Chuangji, Li, Shizhuo, Luttmer, Reed, Singh, Shreya, Yampolsky, Maria, Parikh, Naman, Zhao, Yi, Chen, Meiyi, Huang, Scarlett, Mohanty, Anishka, Johnson, Gregory, Mackey, John, Lin, Jionghao, Koedinger, Ken
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.16778
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914049342570496
author Chen, Eason
Judicke, Sophia
Beigh, Kayla
Tang, Xinyi
Xiao, Zimo
Li, Chuangji
Li, Shizhuo
Luttmer, Reed
Singh, Shreya
Yampolsky, Maria
Parikh, Naman
Zhao, Yi
Chen, Meiyi
Huang, Scarlett
Mohanty, Anishka
Johnson, Gregory
Mackey, John
Lin, Jionghao
Koedinger, Ken
author_facet Chen, Eason
Judicke, Sophia
Beigh, Kayla
Tang, Xinyi
Xiao, Zimo
Li, Chuangji
Li, Shizhuo
Luttmer, Reed
Singh, Shreya
Yampolsky, Maria
Parikh, Naman
Zhao, Yi
Chen, Meiyi
Huang, Scarlett
Mohanty, Anishka
Johnson, Gregory
Mackey, John
Lin, Jionghao
Koedinger, Ken
contents We evaluate the effectiveness of LLM-Tutor, a large language model (LLM)-powered tutoring system that combines an AI-based proof-review tutor for real-time feedback on proof-writing and a chatbot for mathematics-related queries. Our experiment, involving 148 students, demonstrated that the use of LLM-Tutor significantly improved homework performance compared to a control group without access to the system. However, its impact on exam performance and time spent on tasks was found to be insignificant. Mediation analysis revealed that students with lower self-efficacy tended to use the chatbot more frequently, which partially contributed to lower midterm scores. Furthermore, students with lower self-efficacy were more likely to engage frequently with the proof-review-AI-tutor, a usage pattern that positively contributed to higher final exam scores. Interviews with 19 students highlighted the accessibility of LLM-Tutor and its effectiveness in addressing learning needs, while also revealing limitations and concerns regarding potential over-reliance on the tool. Our results suggest that generative AI alone like chatbot may not suffice for comprehensive learning support, underscoring the need for iterative design improvements with learning sciences principles with generative AI educational tools like LLM-Tutor.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16778
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative AI alone may not be enough: Evaluating AI Support for Learning Mathematical Proof
Chen, Eason
Judicke, Sophia
Beigh, Kayla
Tang, Xinyi
Xiao, Zimo
Li, Chuangji
Li, Shizhuo
Luttmer, Reed
Singh, Shreya
Yampolsky, Maria
Parikh, Naman
Zhao, Yi
Chen, Meiyi
Huang, Scarlett
Mohanty, Anishka
Johnson, Gregory
Mackey, John
Lin, Jionghao
Koedinger, Ken
Human-Computer Interaction
We evaluate the effectiveness of LLM-Tutor, a large language model (LLM)-powered tutoring system that combines an AI-based proof-review tutor for real-time feedback on proof-writing and a chatbot for mathematics-related queries. Our experiment, involving 148 students, demonstrated that the use of LLM-Tutor significantly improved homework performance compared to a control group without access to the system. However, its impact on exam performance and time spent on tasks was found to be insignificant. Mediation analysis revealed that students with lower self-efficacy tended to use the chatbot more frequently, which partially contributed to lower midterm scores. Furthermore, students with lower self-efficacy were more likely to engage frequently with the proof-review-AI-tutor, a usage pattern that positively contributed to higher final exam scores. Interviews with 19 students highlighted the accessibility of LLM-Tutor and its effectiveness in addressing learning needs, while also revealing limitations and concerns regarding potential over-reliance on the tool. Our results suggest that generative AI alone like chatbot may not suffice for comprehensive learning support, underscoring the need for iterative design improvements with learning sciences principles with generative AI educational tools like LLM-Tutor.
title Generative AI alone may not be enough: Evaluating AI Support for Learning Mathematical Proof
topic Human-Computer Interaction
url https://arxiv.org/abs/2509.16778