| 陆驰,韩明跃,张坤,冯雪.多模型协同驱动的学术论文智能编校工作流构建与效能评价.编辑学报,2026,38(4):466-474 |
| 多模型协同驱动的学术论文智能编校工作流构建与效能评价 |
| Construction and efficiency evaluation of an intelligent editing and proofreading workflow for academic papers collaboratively driven by multiple large language models |
| |
| DOI：10.16811/j.cnki.1001-4314.2026.04.010 |
| 中文关键词: 大语言模型 协同 工作流 智能编校 长文本 学术论文 |
| 英文关键词: large language model collaboration workflow intelligent editing and proofreading long text academic papers |
| 基金项目:年度中华出版促进会研究课题（教育新闻出版专项）重点课题（2025ZBCH-JYZD05）；中国科学技术期刊编辑学会2025年“长江文库计划”编辑学研究项目（CESSP-CJWK-2025005） |
|
| 摘要点击次数: 199 |
| 全文下载次数: 35 |
| 中文摘要: |
| 本研究旨在构建一个由多模型协同驱动的智能编校工作流，以提升编校质量、效率和自动化水平。基于5类编校差错案例库，对10种具备长文本处理能力的大语言模型开展性能测评，依托Dify平台构建多模型协同编校工作流（MLC-EPW），并选取2篇具有代表性的学术论文作为测试对象进行实证对比分析。MLC-EPW的编校质量最优，总体差错正确识别率和修正率均最高，且差错错误识别率较低；MLC-EPW的编校效能最高，处理单篇论文仅需约12 min，成本11~13元/篇。本研究构建的MLC-EPW有效整合了不同大语言模型的优势，在编校质量、效率与成本方面均优于单一模型方案，为学术期刊实现智能化、自动化编校流程提供了可行的技术路径与实践参考。 |
| 英文摘要: |
| This study endeavors to devise a multi-LLM （Large Language Model） collaboratively powered intelligent editing and proofreading workflow， with the objective of elevating the quality， efficiency， and automation of the editing and proofreading procedures. Utilizing a case library encompassing five categories of editing and proofreading errors， we conducted performance evaluations on ten large language models renowned for their long-text processing capabilities. Leveraging the Dify platform， we constructed a multi-LLM collaborative editing and proofreading workflow （MLC-EPW） and selected two representative academic papers as test cases for an empirical comparative analysis. The MLC-EPW exhibited exceptional editing and proofreading performance， achieving the highest overall accuracy rates in error detection and correction while maintaining a comparatively low false-positive rate. Regarding efficiency， the MLC-EPW processed individual papers in around 12 minutes， with costs fluctuating between 11 and 13 CNY per paper. The MLC-EPW developed in this study effectively harnesses the combined strengths of various LLM， surpassing single-model methods in terms of editing and proofreading quality， efficiency， and cost-efficiency. This offers a viable technical pathway and practical reference for academic journals to implement intelligent and automated editing processes. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
