Ensemble ToT of LLMs and Its Application to Automatic Grading System for Supporting Self-Learning
This work addresses the need for better automated grading to support student self-learning, but it is incremental as it builds on existing LLM-based methods by adding ensemble techniques.
The paper tackles the problem of limited performance in LLM-based grading systems by proposing Ensemble Tree-of-Thought (ToT), a framework that integrates multiple models to enhance outputs, resulting in a grading system that provides accurate and explainable feedback for self-learning.
Providing students with detailed and timely grading feedback is essential for self-learning. While existing LLM-based grading systems are promising, most of them rely on one single model, which limits their performance. To address this, we propose Ensemble Tree-of-Thought (ToT), a framework that enhances LLM outputs by integrating multiple models. Using this framework, we develop a grading system. Ensemble ToT follows three steps: (1) analyzing LLM performance, (2) generating candidate answers, and (3) refining them into a final result. Based on this, our grading system first evaluates the grading tendencies of LLMs, then generates multiple results, and finally integrates them via a simulated debate. Experimental results demonstrate our approach's ability to provide accurate and explainable grading by effectively coordinating multiple LLMs.