Preprint · 2026 · Open access

Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers

Mingmeng Geng, Yuhang Dong, Thierry Poibeau

arXiv (Cornell University) · Published 26 March 2026 · DOI 10.48550/arxiv.2603.25638

Open PDFView at the publisherCite this paper

In brief

“Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers” is a 2026 preprint by Mingmeng Geng and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
39
Authors
3

Abstract

Through an analysis of arXiv papers, we report several shifts in word usage that are likely driven by large language models (LLMs) but have not previously received sufficient attention, such as the increased frequency of "beyond" and "via" in titles and the decreased frequency of "the" and "of" in abstracts. Due to the similarities among different LLMs, experiments show that current classifiers struggle to accurately determine which specific model generated a given text in multi-class classification tasks. Meanwhile, variations across LLMs also result in evolving patterns of word usage in academic papers. By adopting a direct and highly interpretable linear approach and accounting for differences between models and prompts, we quantitatively assess these effects and show that real-world LLM usage is heterogeneous and dynamic.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Geng, M., Dong, Y., & Poibeau, T. (2026). Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.25638

MLA 9

Geng, Mingmeng, et al. “Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2603.25638.

Chicago

Geng, Mingmeng, Yuhang Dong, and Thierry Poibeau. 2026. “Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.25638.

Harvard

Geng, M., Dong, Y. and Poibeau, T. (2026) ‘Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers’, arXiv (Cornell University). doi:10.48550/arxiv.2603.25638.

IEEE

M. Geng, Y. Dong, and T. Poibeau, “Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2603.25638.

BibTeX

@misc{geng2026beyond,
  title     = {{Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers}},
  author    = {Geng, Mingmeng and Dong, Yuhang and Poibeau, Thierry},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2603.25638},
  url       = {https://doi.org/10.48550/arxiv.2603.25638}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling

  • large language models
  • academic papers
  • LLM-generated text
  • arXiv
  • multi-class classification
  • prompt effects
  • model heterogeneity

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Geng, M., Dong, Y., & Poibeau, T. (2026). Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.25638

How many times has this paper been cited?

1 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Mingmeng Geng, Yuhang Dong, Thierry Poibeau.

What is the DOI of this paper?

10.48550/arxiv.2603.25638, permanently at https://doi.org/10.48550/arxiv.2603.25638. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.