Chinese Essay Rhetoric Recognition Using LoRA, In-context Learning and Model Ensemble
This work provides a practical solution for automated essay scoring in Chinese education, though it is an incremental application of existing methods to a specific domain.
The authors tackled Chinese essay rhetoric recognition using LLMs with LoRA fine-tuning and in-context learning, achieving first place on all three tracks of the CCL 2025 evaluation task.
Rhetoric recognition is a critical component in automated essay scoring. By identifying rhetorical elements in student writing, AI systems can better assess linguistic and higher-order thinking skills, making it an essential task in the area of AI for education. In this paper, we leverage Large Language Models (LLMs) for the Chinese rhetoric recognition task. Specifically, we explore Low-Rank Adaptation (LoRA) based fine-tuning and in-context learning to integrate rhetoric knowledge into LLMs. We formulate the outputs as JSON to obtain structural outputs and translate keys to Chinese. To further enhance the performance, we also investigate several model ensemble methods. Our method achieves the best performance on all three tracks of CCL 2025 Chinese essay rhetoric recognition evaluation task, winning the first prize.