Ensemble ToT of LLMs and Its Application to Automatic Grading System for Supporting Self-Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917934250590208 |
|---|---|
| author | Ito, Yuki Ma, Qiang |
| author_facet | Ito, Yuki Ma, Qiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16399 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ensemble ToT of LLMs and Its Application to Automatic Grading System for Supporting Self-Learning Ito, Yuki Ma, Qiang Information Retrieval Artificial Intelligence Computation and Language I.2.7; K.3.1; K.3.2 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. |
| title | Ensemble ToT of LLMs and Its Application to Automatic Grading System for Supporting Self-Learning |
| topic | Information Retrieval Artificial Intelligence Computation and Language I.2.7; K.3.1; K.3.2 |
| url | https://arxiv.org/abs/2502.16399 |