现代信息科技2025，Vol.9Issue(11)：38-42,48,6.DOI:10.19850/j.cnki.2096-4706.2025.11.008
基于BERT模型与RLHF的大语言模型协同校对方法研究
Research on Collaborative Proofreading Method of Large Language Model Based on BERT Model and RLHF
吴边 1杨政潭 2李翔2
作者信息
- 1. 国网湖北省电力有限公司,湖北 武汉 430048
- 2. 武汉光谷信息技术股份有限公司,湖北 武汉 430206
- 折叠
摘要
Abstract
The accuracy of document proofreading has always faces challenges at the level of complex logic.In order to alleviate the pressure on writers and front-line staff,this study proposes a proofreading method based on multi-model collaboration.The word-by-word label is generated by fine-tuning BERT model,and the Large Language Model is fine-tuning using LoRA to compensate for deficiencies in deep error understanding.The PPO algorithm is used to optimize the decision-making process of the model to meet the needs of different scenarios.The multi-model output results are integrated through XGBoost to avoid underreporting and misreporting.The experimental results show that this method has significant advantages in improving the quality and accuracy of document proofreading.关键词
公文校对/BERT/LLM/PPO/XGBoostKey words
document proofreading/BERT/LLM/PPO/XGBoost分类
计算机与自动化引用本文复制引用
吴边,杨政潭,李翔..基于BERT模型与RLHF的大语言模型协同校对方法研究[J].现代信息科技,2025,9(11):38-42,48,6.
