Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909708731809792 |
|---|---|
| author | Song, Siyu Liu, Wentao Lu, Ye Zhang, Ruohua Liu, Tao Lv, Jinze Wang, Xinyun Zhou, Aimin Tan, Fei Jiang, Bo Hao, Hao |
| author_facet | Song, Siyu Liu, Wentao Lu, Ye Zhang, Ruohua Liu, Tao Lv, Jinze Wang, Xinyun Zhou, Aimin Tan, Fei Jiang, Bo Hao, Hao |
| contents | The integration of large language models (LLMs) into education presents unprecedented opportunities for scalable personalized learning. However, standard LLMs often function as generic information providers, lacking alignment with fundamental pedagogical principles such as helpfulness, student-centered personalization, and creativity cultivation. To bridge this gap, we propose EduAlign, a novel framework designed to guide LLMs toward becoming more effective and responsible educational assistants. EduAlign consists of two main stages. In the first stage, we curate a dataset of 8k educational interactions and annotate them-both manually and automatically-along three key educational dimensions: Helpfulness, Personalization, and Creativity (HPC). These annotations are used to train HPC-RM, a multi-dimensional reward model capable of accurately scoring LLM outputs according to these educational principles. We further evaluate the consistency and reliability of this reward model. In the second stage, we leverage HPC-RM as a reward signal to fine-tune a pre-trained LLM using Group Relative Policy Optimization (GRPO) on a set of 2k diverse prompts. We then assess the pre- and post-finetuning models on both educational and general-domain benchmarks across the three HPC dimensions. Experimental results demonstrate that the fine-tuned model exhibits significantly improved alignment with pedagogical helpfulness, personalization, and creativity stimulation. This study presents a scalable and effective approach to aligning LLMs with nuanced and desirable educational traits, paving the way for the development of more engaging, pedagogically aligned AI tutors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20335 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement Learning Song, Siyu Liu, Wentao Lu, Ye Zhang, Ruohua Liu, Tao Lv, Jinze Wang, Xinyun Zhou, Aimin Tan, Fei Jiang, Bo Hao, Hao Machine Learning Artificial Intelligence The integration of large language models (LLMs) into education presents unprecedented opportunities for scalable personalized learning. However, standard LLMs often function as generic information providers, lacking alignment with fundamental pedagogical principles such as helpfulness, student-centered personalization, and creativity cultivation. To bridge this gap, we propose EduAlign, a novel framework designed to guide LLMs toward becoming more effective and responsible educational assistants. EduAlign consists of two main stages. In the first stage, we curate a dataset of 8k educational interactions and annotate them-both manually and automatically-along three key educational dimensions: Helpfulness, Personalization, and Creativity (HPC). These annotations are used to train HPC-RM, a multi-dimensional reward model capable of accurately scoring LLM outputs according to these educational principles. We further evaluate the consistency and reliability of this reward model. In the second stage, we leverage HPC-RM as a reward signal to fine-tune a pre-trained LLM using Group Relative Policy Optimization (GRPO) on a set of 2k diverse prompts. We then assess the pre- and post-finetuning models on both educational and general-domain benchmarks across the three HPC dimensions. Experimental results demonstrate that the fine-tuned model exhibits significantly improved alignment with pedagogical helpfulness, personalization, and creativity stimulation. This study presents a scalable and effective approach to aligning LLMs with nuanced and desirable educational traits, paving the way for the development of more engaging, pedagogically aligned AI tutors. |
| title | Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.20335 |