Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

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.

arXiv commentConditionally Accepted at CHI 2024

References in corpus (15)

• Survey of Hallucination in Natural Language Generation
• PaLM: Scaling Language Modeling with Pathways
• Emergent Abilities of Large Language Models
• StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement
• GPT-3-driven pedagogical agents for training children's curious question-asking skills
• Large Language Models Can Be Easily Distracted by Irrelevant Context
• Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
• Lost in the Middle: How Language Models Use Long Contexts
• HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
• Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
• ALL-IN-ONE: Multi-Task Learning BERT models for Evaluating Peer Assessments
• Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation
• Solving Math Word Problems by Combining Language Models With Symbolic Solvers
• Automatic Story Generation: Challenges and Attempts
• Towards Reliable and Fluent Large Language Models: Incorporating Feedback Learning Loops in QA Systems

Cited by in corpus (12)

• Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature
• PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning
• Vision-Based Multimodal Interfaces: A Survey and Taxonomy for Enhanced Context-Aware System Design
• SET-PAiREd: Designing for Parental Involvement in Learning with an AI-Assisted Educational Robot
• Beyond Productivity: Rethinking the Impact of Creativity Support Tools
• Characterizing LLM-Empowered Personalized Story-Reading and Interaction for Children: Insights from Multi-Stakeholder Perspectives
• Colin: A Multimodal Human-AI Co-Creation Storytelling System To Support Children's Multi-Level Narrative Skills
• Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation
• BrickSmart: Leveraging Generative AI to Support Children's Spatial Language Learning in Family Block Play
• Once Upon an AI: Six Scaffolds for Child-AI Interaction Design, Inspired by Disney
• Empowering Children to Create AI-Enabled Augmented Reality Experiences
• BotDirector: Robot Storytelling Across the Symmetrical Reality with Multi-modal Interactions