用于人工智能辅助学术创作的出版基础设施。

A publishing infrastructure for AI-assisted academic authoring.

作者信息

Pividori Milton, Greene Casey S

机构信息

Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA · Funded by The National Human Genome Research Institute, K99 HG011898; The Eunice Kennedy Shriver National Institute of Child Health and Human Development, R01 HD109765.

Center for Health AI, University of Colorado School of Medicine, Aurora, CO 80045, USA; Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO 80045, USA · Funded by The Gordon and Betty Moore Foundation, GBMF4552; The National Human Genome Research Institute, R01 HG010067; The Eunice Kennedy Shriver National Institute of Child Health and Human Development, R01 HD109765.

出版信息

bioRxiv. 2023 Jan 23:2023.01.21.525030. doi: 10.1101/2023.01.21.525030.

DOI:10.1101/2023.01.21.525030

PMID:36747665

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9900745/

Abstract

In this work we investigate how models with advanced natural language processing capabilities can be used to reduce the time-consuming process of writing and revising scholarly manuscripts. To this end, we integrate large language models into the Manubot publishing ecosystem to suggest revisions for scholarly text. We tested our AI-based revision workflow in three case studies of existing manuscripts, including the present one. Our results suggest that these models can capture the concepts in the scholarly text and produce high-quality revisions that improve clarity. Given the amount of time that researchers put into crafting prose, we anticipate that this advance will revolutionize the type of knowledge work performed by academics.

摘要

在这项工作中，我们研究了具有先进自然语言处理能力的模型如何能够用于减少撰写和修订学术手稿这一耗时的过程。为此，我们将大语言模型集成到Manubot出版生态系统中，以对学术文本提出修订建议。我们在包括本文在内的三篇现有手稿的案例研究中测试了我们基于人工智能的修订工作流程。我们的结果表明，这些模型能够理解学术文本中的概念，并生成高质量的修订内容，从而提高清晰度。考虑到研究人员投入在精心撰写文章上的时间，我们预计这一进展将彻底改变学者们所从事的知识工作类型。