Chinese Essay Rhetoric Recognition Using LoRA, In-context Learning and Model Ensemble

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Yuxuan, Wang, Xiajing, Zheng, Chen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908967335100416
author Lai, Yuxuan
Wang, Xiajing
Zheng, Chen
author_facet Lai, Yuxuan
Wang, Xiajing
Zheng, Chen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14167
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Chinese Essay Rhetoric Recognition Using LoRA, In-context Learning and Model Ensemble
Lai, Yuxuan
Wang, Xiajing
Zheng, Chen
Computation and Language
Artificial Intelligence
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.
title Chinese Essay Rhetoric Recognition Using LoRA, In-context Learning and Model Ensemble
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.14167