Annotation Guidelines-Based Knowledge Augmentation: Towards Enhancing Large Language Models for Educational Text Classification
This work addresses the need for better automated classification of educational text to analyze learning engagement, which is important for researchers in NLP and education, though it is incremental as it builds on existing LLM methods with a specific augmentation technique.
The study tackled the problem of improving large language models (LLMs) for educational text classification by proposing the Annotation Guidelines-based Knowledge Augmentation (AGKA) approach, which enhances non-fine-tuned LLMs like GPT 4.0 and Llama 3 70B, with GPT 4.0 outperforming fine-tuned models like BERT and RoBERTa on binary classification datasets but lagging in multi-class tasks.
Various machine learning approaches have gained significant popularity for the automated classification of educational text to identify indicators of learning engagement -- i.e. learning engagement classification (LEC). LEC can offer comprehensive insights into human learning processes, attracting significant interest from diverse research communities, including Natural Language Processing (NLP), Learning Analytics, and Educational Data Mining. Recently, Large Language Models (LLMs), such as ChatGPT, have demonstrated remarkable performance in various NLP tasks. However, their comprehensive evaluation and improvement approaches in LEC tasks have not been thoroughly investigated. In this study, we propose the Annotation Guidelines-based Knowledge Augmentation (AGKA) approach to improve LLMs. AGKA employs GPT 4.0 to retrieve label definition knowledge from annotation guidelines, and then applies the random under-sampler to select a few typical examples. Subsequently, we conduct a systematic evaluation benchmark of LEC, which includes six LEC datasets covering behavior classification (question and urgency level), emotion classification (binary and epistemic emotion), and cognition classification (opinion and cognitive presence). The study results demonstrate that AGKA can enhance non-fine-tuned LLMs, particularly GPT 4.0 and Llama 3 70B. GPT 4.0 with AGKA few-shot outperforms full-shot fine-tuned models such as BERT and RoBERTa on simple binary classification datasets. However, GPT 4.0 lags in multi-class tasks that require a deep understanding of complex semantic information. Notably, Llama 3 70B with AGKA is a promising combination based on open-source LLM, because its performance is on par with closed-source GPT 4.0 with AGKA. In addition, LLMs struggle to distinguish between labels with similar names in multi-class classification.