EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Contrasting Linguistic Patterns in Human and LLM-Generated News Text

Alberto Muñoz-Ortiz, Carlos Gómez-Rodríguez, David Vilares

Artificial Intelligence Review · 23.08.2024 · 57 (10)

DOI: 10.1007/s10462-024-10903-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence Review, online erschienen am 23.08.2024. Verfasst von Alberto Muñoz-Ortiz und 2 weiteren Autor:innen. Beteiligte Einrichtung: Universidade da Coruña, CITIC, Departamento de Ciencias de la Computación y Tecnologías de la Información, Campus de Elviña s/n, A Coruña, 15071 A Co…. Die Arbeit wurde bisher 89-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Estatal de Investigación,Spain, Xunta de Galicia, Centro de Investigación en Tecnologías de la Información y las Comunicaciones.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from six different LLMs that cover three different families and four sizes in total. Our analysis spans several measurable linguistic dimensions, including morphological, syntactic, psychometric, and sociolinguistic aspects. The results reveal various measurable differences between human and AI-generated texts. Human texts exhibit more scattered sentence length distributions, more variety of vocabulary, a distinct use of dependency and constituent types, shorter constituents, and more optimized dependency distances. Humans tend to exhibit stronger negative emotions (such as fear and disgust) and less joy compared to text generated by LLMs, with the toxicity of these models increasing as their size grows. LLM outputs use more numbers, symbols and auxiliaries (suggesting objective language) than human texts, as well as more pronouns. The sexist bias prevalent in human text is also expressed by LLMs, and even magnified in all of them but one. Differences between LLMs and humans are larger than between LLMs.

Schlagwörter

Stichwörter der Autor:innen

Computational linguisticsLarge language modelsLinguistic biasesMachine-generated text

Autor:innen und Institutionen

  • Universidade da Coruña, CITIC, Departamento de Ciencias de la Computación y Tecnologías de la Información, Campus de Elviña s/n, A Coruña, 15071 A Coruña Spain.

Förderung

  • Agencia Estatal de Investigación,Spain
  • Xunta de Galicia
  • Centro de Investigación en Tecnologías de la Información y las Comunicaciones
  • Agencia Estatal de Investigación
  • HORIZON EUROPE European Research Council
  • Universidade da Coruña

Zitieren

APA

Muñoz-Ortiz, A., Gómez-Rodríguez, C., & Vilares, D. (2024). Contrasting Linguistic Patterns in Human and LLM-Generated News Text. Artificial Intelligence Review, 57(10). https://doi.org/10.1007/s10462-024-10903-2

Vancouver

Muñoz-Ortiz A, Gómez-Rodríguez C, Vilares D. Contrasting Linguistic Patterns in Human and LLM-Generated News Text. Artificial Intelligence Review. 2024;57(10). doi:10.1007/s10462-024-10903-2

BibTeX
@article{MuozOrtiz2024,
  author = {Muñoz-Ortiz, Alberto and Gómez-Rodríguez, Carlos and Vilares, David},
  title = {Contrasting Linguistic Patterns in Human and LLM-Generated News Text},
  journal = {Artificial Intelligence Review},
  year = {2024},
  volume = {57},
  number = {10},
  doi = {10.1007/s10462-024-10903-2}
}
Kostenlos starten →