Knowledge Distillation of LLM for Education

This study proposes a method for distilling the knowledge of fine-tuned Large Language Models (LLMs) into a smaller, more efficient, and accurate neural network, specifically targeting the challenge of deploying these models on resource-constrained devices. Our methodology involves training the smaller student model using the prediction probabilities of the LLM, which serves as a teacher model. This is achieved through a specialized loss function tailored to learn from the LLM's output probabilities, ensuring that the student model closely mimics the teacher's performance. To test this approach, we utilized a large dataset, 7T, containing 6,684 student-written responses to science questions and three other datasets with student-written responses. We also compared performance with original neural network (NN) models to validate the accuracy. Results have shown that the NN and distilled student models have comparable accuracy to the teacher model for the 7T dataset; however, other datasets have shown significantly lower accuracy (28% on average) for NN, though our proposed distilled model is still able to achieve 12\% higher accuracy than NN. Furthermore, the student model size ranges from 0.1M to 0.02M, 100 times smaller in terms of parameters and ten times smaller compared with the original output model size. The significance of this research lies in its potential to make advanced AI technologies accessible in typical educational settings, particularly for automatic scoring.

Using GPT-4 to Augment Unbalanced Data for Automatic Scoring

Machine learning-based automatic scoring can be challenging if students' responses are unbalanced across scoring categories, as it introduces uncertainty in the machine training process. To meet this challenge, we introduce a novel text data augmentation framework leveraging GPT-4, a generative large language model, specifically tailored for unbalanced datasets in automatic scoring. Our experimental dataset comprised student written responses to two science items. We crafted prompts for GPT-4 to generate responses resembling student written answers, particularly for the minority scoring classes, to augment the data. We then finetuned DistillBERT for automatic scoring based on the augmented and original datasets. Model performance was assessed using accuracy, precision, recall, and F1 metrics. Our findings revealed that incorporating GPT-4-augmented data remarkedly improved model performance, particularly for precision, recall, and F1 scores. Interestingly, the extent of improvement varied depending on the specific dataset and the proportion of augmented data used. Notably, we found that a varying amount of augmented data (5\%-40\%) was needed to obtain stable improvement for automatic scoring. We also compared the accuracies of models trained with GPT-4 augmented data to those trained with additional student-written responses. Results suggest that the GPT-4 augmented scoring models outperform or match the models trained with student-written augmented data. This research underscores the potential and effectiveness of data augmentation techniques utilizing generative large language models--GPT-4 in addressing unbalanced datasets within automated assessment.