arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.14852cs.CL
收藏

ArcGPT:专为真实世界档案应用定制的大型语言模型

ArcGPT: A Large Language Model Tailored for Real-world Archival Applications

Wuhan University(武汉大学);Loughborough University(拉夫堡大学)

Shitou Zhang, Jingrui Hou, Siyuan Peng, Zuchao Li, Qibiao Hu, Ping Wang

AI总结:

本文提出首个专为档案领域定制的通用大语言模型ArcGPT,通过在海量档案数据上预训练,并发布包含四项真实任务的AMBLE基准,证明其超越现有模型,有效提升档案数据管理效率。

摘要:

档案在保存信息和知识方面发挥着关键作用,这类数据的指数级增长需要高效、自动化的工具来管理和利用档案信息资源。档案应用涉及管理海量数据,这些数据难以处理和分析。尽管LLMs在多个领域取得了显著进展,但目前尚无公开可用的档案定制LLM。为填补这一空白,我们引入了ArcGPT,据我们所知,这是首个专为档案领域定制的通用LLM。为了提升模型在真实世界档案任务上的性能,ArcGPT在海量且广泛的档案领域数据上进行了预训练。除ArcGPT外,我们还发布了AMBLE,这是一个包含四项真实世界档案任务的基准。在AMBLE上的评估显示,ArcGPT超越了现有的最先进模型,标志着在有效档案数据管理方面迈出了重要一步。最终,ArcGPT旨在更好地服务档案界,帮助档案工作者履行其保存和利用我们共同信息与知识的关键职责。

英文摘要:

Archives play a crucial role in preserving information and knowledge, and the exponential growth of such data necessitates efficient and automated tools for managing and utilizing archive information resources. Archival applications involve managing massive data that are challenging to process and analyze. Although LLMs have made remarkable progress in diverse domains, there are no publicly available archives tailored LLM. Addressing this gap, we introduce ArcGPT, to our knowledge, the first general-purpose LLM tailored to the archival field. To enhance model performance on real-world archival tasks, ArcGPT has been pre-trained on massive and extensive archival domain data. Alongside ArcGPT, we release AMBLE, a benchmark comprising four real-world archival tasks. Evaluation on AMBLE shows that ArcGPT outperforms existing state-of-the-art models, marking a substantial step forward in effective archival data management. Ultimately, ArcGPT aims to better serve the archival community, aiding archivists in their crucial role of preserving and harnessing our collective information and knowledge.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑