Qian Shen, Fanghua Cao, Min Yao, Shlok Gilda, Bonnie J. Dorr, Walter L. Leite (2026) — University of Florida. BEA 2026 @ ACL 2026.
Key Finding: Small Fine-Tuned Models Beat Large Zero-Shot Models
Using an expert-designed children's reading curriculum and stories generated by GPT-4o and Llama 3.3 70B as training data, the authors fine-tuned three different 8B-parameter LLMs. The fine-tuned 8B models outperformed zero-shot GPT-4o and Llama 3.3 70B on difficulty-related metrics while showing negligible safety issues.
The Controllability-over-Scale Paradigm
The core philosophy is controllability over scale: a compact, affordable model can be fine-tuned to target specific reading levels and error patterns, something large general-purpose models cannot do out of the box. This has major implications for equity-in-ai-education — schools could run these models locally at low cost rather than depending on expensive API-based LLMs.
Educational Deployment
The generated stories were designed for use by teachers, parents, and children in classrooms and at home. The controllable difficulty enables personalized-learning at scale — matching reading materials to individual student proficiency levels. The safety guarantees address concerns in ai-tutor-safety-harms.
Methodological Contribution
Fine-tuning designs were systematically compared, with the curriculum-derived training data providing curriculum alignment that general-purpose models lack. The quantitative and qualitative evaluation framework provides a template for assessing AI-generated educational content.
Related Pages
- vocabulary-difficulty-prediction — LLM fine-tuned with soft-target loss achieves r>0.91 for vocabulary difficulty p
- language-learning — Reading instruction and literacy development
- k-12-ai-education — Classroom and home deployment for children
- ai-literacy — AI-generated reading materials and student-AI interaction
- scaffolding — Difficulty-controlled stories as reading scaffolds
- personalized-learning — Matching story difficulty to student level
- llm-student-modeling-memory — Compact LLM deployment as alternative to large API models
Citation
APA: Shen, Q., Cao, F., Yao, M., Gilda, S., Dorr, B. J., & Leite, W. L. (2026). Children's English reading story generation via supervised fine-tuning of compact LLMs with controllable difficulty and safety. Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026). arXiv:2605.13709.