Enhancing Chinese Essay Discourse Logic Evaluation Through Optimized Fine-Tuning of Large Language Models

被引：0

作者：

Song, Jinwang ^{[1
]}

Song, Yanxin ^{[1
]}

Zhou, Guangyu ^{[1
]}

Fu, Wenhui ^{[1
]}

Zhang, Kunli ^{[1
]}

Zan, Hongying ^{[1
]}

机构：

[1] Zhengzhou Univ, Zhengzhou, Peoples R China

来源：

NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING, PT V, NLPCC 2024 | 2025年 / 15363卷

关键词：

Essay Evaluation; Large Language Models; Natural Language Processing;

D O I：

10.1007/978-981-97-9443-0_30

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Due to the high complexity and diversity of writing, automated essay evaluation systems face significant challenges. Large language models (LLMs), representing the latest peak in NLP technology for semantic understanding, hold immense potential for advancing essay evaluation systems. In the NLPCC 2024 Shared Task 4 Chinese Essay Discourse Logic Evaluation and Integration, we investigated improving LLMs' capabilities in evaluating essay logic, coherence, and quality. Considering the characteristics of different tasks, we adopted MRC-style instructions to optimize output formats and implemented undersampling to address data imbalance. To enhance efficiency and model performance, we explored LLM fine-tuning methods that decouple tasks and applied similarity comparison to refine model outputs. Additionally, we utilized noisy embedding fine-tuning to mitigate overfitting. Our approach achieved the top ranking in the NLPCC 2024 Shared Task 4.

引用

页码：342 / 352

页数：11

共 50 条

[41] Fine-Tuning Large Language Models to Improve Accuracy and Comprehensibility of Automated Code Review
Yu, Yongda
Rong, Guoping
Shen, Haifeng
Zhang, He
Shao, Dong
Wang, Min
Wei, Zhao
Xu, Yong
Wang, Juhong
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, 2025, 34 (01)
[42] Fine-Tuning and Evaluating Open-Source Large Language Models for the Army Domain
Ruiz, Maj Daniel C.
Sell, John
arXiv,
[43] Characterizing Communication in Distributed Parameter-Efficient Fine-Tuning for Large Language Models
Alnaasan, Nawras
Huang, Horng-Ruey
Shafi, Aamir
Subramoni, Hari
Panda, Dhabaleswar K.
2024 IEEE SYMPOSIUM ON HIGH-PERFORMANCE INTERCONNECTS, HOTI 2024, 2024, : 11 - 19
[44] Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values
Schoch, Stephanie
Mishra, Ritwick
Ji, Yangfeng
PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-SRW 2023, VOL 4, 2023, : 266 - 275
[45] An Empirical Study on Fine-tuning Large Language Models of Code for Automated Program Repair
Huang, Kai
Meng, Xiangxin
Zhang, Jian
Liu, Yang
Wang, Wenjie
Li, Shuhao
Zhang, Yuqing
2023 38TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING, ASE, 2023, : 1162 - 1174
[46] SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
Thangarasa, Vithursan
Gupta, Abhay
Marshall, William
Li, Tianda
Leong, Kevin
DeCoste, Dennis
Lie, Sean
Saxena, Shreyas
UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2023, 216 : 2134 - 2146
[47] Research on Fine-Tuning Optimization Strategies for Large Language Models in Tabular Data Processing
Zhao, Xiaoyong
Leng, Xingxin
Wang, Lei
Wang, Ningning
BIOMIMETICS, 2024, 9 (11)
[48] Enhancing AAV Viability Prediction: A Generalizable Fine-Tuning Framework with Large Language Model xTrimoPGLM
Yang, Qirong
Zou, Diming
Guo, Yucheng
Xu, Chenrui
Marsic, Damien
Cai, Zhongshan
Liu, Yawen
Xu, Ziyao
Qu, Vicky
Garces, Fernando
Greisen, Per
Ji, Qingzhou
Song, Le
MOLECULAR THERAPY, 2024, 32 (04) : 693 - 694
[49] Enhancing Outcome Prediction By Fine-Tuning Contextual Language Models on Diverse Cancer Patient Notes
Srinivas, B.
Anil, S.
Liu, B.
Interian, Y.
Chen, W.
Lupo, J.
Braunstein, S.
Morin, O.
Lin, H.
MEDICAL PHYSICS, 2024, 51 (09) : 6590 - 6591
[50] PETALS: Collaborative Inference and Fine-tuning of Large Models
Borzunov, Alexander
Baranchuk, Dmitry
Dettmers, Tim
Ryabinin, Max
Belkada, Younes
Chumachenko, Artem
Samygin, Pavel
Raffel, Colin
PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-DEMO 2023, VOL 3, 2023, : 558 - 568

← 1 2 3 4 5 →