Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling
Chao Zhang, Xuechen Liu, Katherine Ziska, Soobin Jeon, Chi-Lin Yu, Ying Xu
Abstract
Mathematical language is a cornerstone of a child’s mathematical development, and children can effectively acquire this language through storytelling with a knowledgeable and engaging partner. In this study, we leverage the recent advances in large language models to conduct free-form, creative conversations with children. Consequently, we developed Mathemyths, a joint storytelling agent that takes turns co-creating stories with children while integrating mathematical terms into the evolving narrative. This paper details our development process, illustrating how prompt-engineering can optimize LLMs for educational contexts. Through a user study involving 35 children aged 4-8 years, our results suggest that when children interacted with Mathemyths, their learning of mathematical language was comparable to those who co-created stories with a human partner. However, we observed differences in how children engaged with co-creation partners of different natures. Overall, we believe that LLM applications, like Mathemyths, offer children a unique conversational experience pertaining to focused learning objectives.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers23
- "Don't Forget the Teachers": Towards an Educator-Centered Understanding of Harms from Large Language Models in EducationEmma Harvey, Allison Koenecke, René F. KizilcecCHI 2025 · 63 citations
- Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature ReviewRock Yuren Pang, Hope Schroeder, Kynnedy Simone Smith, Solon Barocas et al.CHI 2025 · 51 citations
- Vision-Based Multimodal Interfaces: A Survey and Taxonomy for Enhanced Context-Aware System DesignYongquan 'Owen' Hu, Jingyu Tang, Xinya Gong, Zhongyi Zhou et al.CHI 2025 · 37 citations
- How CO2STLY Is CHI? The Carbon Footprint of Generative AI in HCI Research and What We Should Do About ItNanna Inie, Jeanette Falk, Raghavendra SelvanCHI 2025 · 33 citations
- Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI LiteratureShuning Zhang, Hui Wang, Xin YiCSCW 2025 · 31 citations
Builds on15
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Large Language Models Can Be Easily Distracted by Irrelevant ContextFreda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales et al.ICML 2023 · 970 citations
- Why Johnny Can't Prompt: How Non-AI Experts Try (and Fail) to Design LLM PromptsJ. D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, Qian YangCHI 2023 · 892 citations
- HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language ModelsJunyi Li, Xiaoxue Cheng, Xin Zhao, Jian-Yun Nie et al.EMNLP 2023 · 224 citations
- TaleBrush: Sketching Stories with Generative Pretrained Language ModelsJohn Joon Young Chung, Wooseok Kim, Kang Min Yoo, Hwaran Lee et al.CHI 2022 · 202 citations
Related papers
- Characterizing LLM-Empowered Personalized Story Reading and Interaction for Children: Insights From Multi-Stakeholder PerspectivesJiaju Chen, Minglong Tang, Yuxuan Lu, Bingsheng Yao et al.CHI 2025 · 20 citations
- Scientific and Fantastical: Creating Immersive, Culturally Relevant Learning Experiences with Augmented Reality and Large Language ModelsAlan Y. Cheng, Meng Guo, Melissa Ran, Arpit Ranasaria et al.CHI 2024 · 37 citations
- MathKingdom: Teaching Children Mathematical Language Through Speaking at Home via a Voice-Guided GameWenjie Xu, Jiayi Ma, Jiayu Yao, Weijia Lin et al.CHI 2023 · 26 citations
- Oak Story: Improving Learner Outcomes with LLM-Mediated Interactive NarrativesAlan Y. Cheng, Carolyn Q. Zou, Anthony Xie, Matthew Hsu et al.UIST 2025 · 2 citations
- CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language ProgrammingLi Feng, Ryan Yen, Yuzhe You, Mingming Fan et al.CHI 2024 · 28 citations
