Scientific publications are the primary means to communicate research discoveries, where the writing quality is of crucial importance. However, prior work studying the human editing process in this domain mainly focused on the abstract or introduction sections, resulting in an incomplete picture. In this work, we provide a complete computational framework for studying text revision in scientific writing. We first introduce arXivEdits, a new annotated corpus of 751 full papers from arXiv with gold sentence alignment across their multiple versions of revision, as well as fine-grained span-level edits and their underlying intentions for 1,000 sentence pairs. It supports our data-driven analysis to unveil the common strategies practiced by researchers for revising their papers. To scale up the analysis, we also develop automatic methods to extract revision at document-, sentence-, and word-levels. A neural CRF sentence alignment model trained on our corpus achieves 93.8 F1, enabling the reliable matching of sentences between different versions. We formulate the edit extraction task as a span alignment problem, and our proposed method extracts more fine-grained and explainable edits, compared to the commonly used diff algorithm. An intention classifier trained on our dataset achieves 78.9 F1 on the fine-grained intent classification task. Our data and system are released at tiny.one/arxivedits.
ParaRev: Building a dataset for Scientific Paragraph Revision annotated with revision instruction
Nantes Université(南特大学);École Centrale Nantes(南特中央理工学院);CNRS(法国国家科学研究中心);LS2N(南特数字科学实验室);JFLI(日本信息学研究所联合实验室);Nantes University(南特大学);National Institute of Informatics(日本信息学研究所)
Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision
New York University(纽约大学);NYU Shanghai(上海纽约大学);University of Alberta(阿尔伯塔大学);Princeton University(普林斯顿大学);University of Waterloo(滑铁卢大学);Verdent AI, Inc.(Verdent AI公司)
CASIMIR: A Corpus of Scientific Articles enhanced with Multiple Author-Integrated Revisions
Nantes Université(南特大学);École Centrale Nantes(南特中央理工学院);CNRS(法国国家科学研究中心);LS2N(南特数字科学实验室);Japanese French Laboratory for Informatics(日法信息学实验室);NII(日本国立信息学研究所)
Topic Modeling the Reading and Writing Behavior of Information Foragers
Indiana University(印第安纳大学)
在主体具有不完全信息的环境中的“信息觅食”的一般问题已经在许多领域中被探索,包括认知心理学、神经科学、经济学、金融学、生态学和计算机科学。在所有这些领域,联合国信息技术中心的目标是通过调查足够的现有知识来确定自己在信息空间中的方向,从而提高未来的业绩。个人可以被看作是在进行认知搜索,在这个过程中,他们必须在探索对他们来说新奇的想法和利用他们已经擅长的领域的知识之间取得平衡。在这篇论文中,我提出了几个案例研究,展示了阅读和写作行为如何相互作用,以构建个人知识库。这些研究使用LDA主题建模来表示每个作者阅读和撰写的文本的信息环境。有三项研究是围绕查尔斯·达尔文展开的。达尔文留下了他23年来读过的每一本书的详细记录,从他离开英国皇家海军舰艇开始。比格尔到《物种起源》出版后不久。此外,他在出版前留下了草稿的副本。我描述了他的阅读行为,然后展示了阅读行为如何与《物种起源》的草稿和后续修订相互作用,并将数据集扩展到包括后来的阅读和写作。然后,通过对托马斯·杰斐逊书信的研究,将研究扩展到非书籍资料。最后,通过对神经科学引文数据的分析,我从个人行为转向了集体行为来构建信息环境。总之,这些研究揭示了“创新发生的个体和集体现象之间的相互作用”(Tria et al. 2014)。
From Model-centered to Human-Centered: Revision Distance as a Metric for Text Evaluation in LLMs-based Applications
School of Information Management, Wuhan University(武汉大学信息管理学院);Institute for Intelligent Computing, Alibaba Group(阿里巴巴集团智能计算研究所);Worcester Polytechnic Institute(伍斯特理工学院)
PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress
University of Oxford(牛津大学);National University of Singapore(新加坡国立大学);Stanford University(斯坦福大学);University of Cambridge(剑桥大学);University of Washington(华盛顿大学)