AI-Assisted Writing Is Growing Fastest Among Non-English-Speaking and Less Established Scientists

• URL: http://arxiv.org/abs/2511.15872v1
• Date: Wed, 19 Nov 2025 21:00:18 GMT
• Title: AI-Assisted Writing Is Growing Fastest Among Non-English-Speaking and Less Established Scientists
• Authors: Jialin Liu, Yongyuan He, Zhihan Zheng, Yi Bu, Chaoqun Ni,
• Abstract summary: We analyze over two million full-text biomedical publications from PubMed Central from 2021 to 2024.<n>We observe a significant post-ChatGPT surge in AI-assisted writing, with adoption growing fastest in contexts where language barriers are most pronounced.<n>Increased AI usage was associated with a modest increase in productivity, narrowing the publication gap between scientists from English-speaking and non-English-speaking countries.
• Score: 2.9557942678513007
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The dominance of English in global science has long created significant barriers for non-native speakers. The recent emergence of generative artificial intelligence (GenAI) dramatically reduces drafting and revision costs, but, simultaneously, raises a critical question: how is the technology being adopted by the global scientific community, and is it mitigating existing inequities? This study provides first large-scale empirical evidence by analyzing over two million full-text biomedical publications from PubMed Central from 2021 to 2024, estimating the fraction of AI-generated content using a distribution-based framework. We observe a significant post-ChatGPT surge in AI-assisted writing, with adoption growing fastest in contexts where language barriers are most pronounced: approximately 400% in non-English-speaking countries compared to 183% in English-speaking countries. This adoption is highest among less-established scientists, including those with fewer publications and citations, as well as those in early career stages at lower-ranked institutions. Prior AI research experience also predicted higher adoption. Finally, increased AI usage was associated with a modest increase in productivity, narrowing the publication gap between scientists from English-speaking and non-English-speaking countries with higher levels of AI adoption. These findings provide large-scale evidence that generative AI is being adopted unevenly, reflecting existing structural disparities while also offering a potential opportunity to mitigate long-standing linguistic inequalities.

Related papers

• Artificial intelligence is creating a new global linguistic hierarchy [34.80252741178931]
  We present a global longitudinal analysis of social, economic and infrastructural conditions across languages.<n>We find that despite efforts to broaden the reach of language technologies, the dominance of a handful of languages is exacerbating disparities.<n>We introduce the Language AI Readiness Index (EQUATE), which maps the state of technological, socio-economic, and infrastructural prerequisites for AI deployment across languages.
  arXiv  Detail & Related papers  (2026-02-12T14:50:44Z)
• Generative AI as a Linguistic Equalizer in Global Science [0.0]
  We provide the first large-scale evidence testing whether generative AI (GenAI) acts as a linguistic equalizer in global science.<n>We compare GenAI-assisted and non-assisted publications from authors in non-English-speaking countries.<n>We find significant and growing convergence for GenAI-assisted publications after the release of ChatGPT in late 2022.
  arXiv  Detail & Related papers  (2025-11-12T08:48:15Z)
• AI Diffusion in Low Resource Language Countries [10.939989206795047]
  Low-Resource Language Countries (LRLCs) have a share of AI users that is approximately 20% lower relative to their baseline.<n> linguistic accessibility is a significant, independent barrier to equitable AI diffusion.
  arXiv  Detail & Related papers  (2025-11-04T17:31:39Z)
• Who Gets Seen in the Age of AI? Adoption Patterns of Large Language Models in Scholarly Writing and Citation Outcomes [1.5702201012657682]
  Authors in the Global East adopt AI tools more aggressively, yet Western authors gain more per unit of adoption due to pre-existing penalties for "humanlike" writing.<n>Prestigious journals continue to privilege more human-sounding texts, creating tensions between visibility and gatekeeping.
  arXiv  Detail & Related papers  (2025-09-10T06:05:34Z)
• Computational Approaches to Understanding Large Language Model Impact on Writing and Information Ecosystems [10.503784446147122]
  Large language models (LLMs) have shown significant potential to change how we write, communicate, and create.<n>This dissertation examines how individuals and institutions are adapting to and engaging with this emerging technology.
  arXiv  Detail & Related papers  (2025-06-20T20:15:09Z)
• A Collection of Innovations in Medical AI for patient records in 2024 [3.663763802269743]
  The field of Artificial Intelligence in healthcare is evolving at an unprecedented pace.<n>This paper advocates for a new category of academic publications that prioritizes the most recent AI driven healthcare innovations.
  arXiv  Detail & Related papers  (2025-02-25T06:24:24Z)
• Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing [55.2480439325792]
  This study systematically evaluations twelve state-of-the-art AI-text detectors using our AI-Polished-Text Evaluation dataset.<n>Our findings reveal that detectors frequently flag even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models.
  arXiv  Detail & Related papers  (2025-02-21T18:45:37Z)
• Hype, Sustainability, and the Price of the Bigger-is-Better Paradigm in AI [67.58673784790375]
  We argue that the 'bigger is better' AI paradigm is not only fragile scientifically, but comes with undesirable consequences.<n>First, it is not sustainable, as, despite efficiency improvements, its compute demands increase faster than model performance.<n>Second, it implies focusing on certain problems at the expense of others, leaving aside important applications, e.g. health, education, or the climate.
  arXiv  Detail & Related papers  (2024-09-21T14:43:54Z)
• Artificial intelligence adoption in the physical sciences, natural sciences, life sciences, social sciences and the arts and humanities: A bibliometric analysis of research publications from 1960-2021 [73.06361680847708]
  In 1960 14% of 333 research fields were related to AI, but this increased to over half of all research fields by 1972, over 80% by 1986 and over 98% in current times. In 1960 14% of 333 research fields were related to AI (many in computer science), but this increased to over half of all research fields by 1972, over 80% by 1986 and over 98% in current times. We conclude that the context of the current surge appears different, and that interdisciplinary AI application is likely to be sustained.
  arXiv  Detail & Related papers  (2023-06-15T14:08:07Z)
• No Language Left Behind: Scaling Human-Centered Machine Translation [69.28110770760506]
  We create datasets and models aimed at narrowing the performance gap between low and high-resource languages. We propose multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. Our model achieves an improvement of 44% BLEU relative to the previous state-of-the-art.
  arXiv  Detail & Related papers  (2022-07-11T07:33:36Z)
• Systematic Inequalities in Language Technology Performance across the World's Languages [94.65681336393425]
  We introduce a framework for estimating the global utility of language technologies. Our analyses involve the field at large, but also more in-depth studies on both user-facing technologies and more linguistic NLP tasks.
  arXiv  Detail & Related papers  (2021-10-13T14:03:07Z)
• CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark [51.38557174322772]
  We present the first Chinese Biomedical Language Understanding Evaluation benchmark. It is a collection of natural language understanding tasks including named entity recognition, information extraction, clinical diagnosis normalization, single-sentence/sentence-pair classification. We report empirical results with the current 11 pre-trained Chinese models, and experimental results show that state-of-the-art neural models perform by far worse than the human ceiling.
  arXiv  Detail & Related papers  (2021-06-15T12:25:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.