EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detecting and Comparing LLM Capabilities to Human Writers Through Linguistic Analysis

Lucas Liebe, Jannis Baum, Tim Barz-Cech, Willy Scheibel, Jürgen Döllner

SN Computer Science · 01.07.2026 · 7 (6)

DOI: 10.1007/s42979-026-05131-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SN Computer Science, online erschienen am 01.07.2026. Verfasst von Lucas Liebe und 4 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universität Potsdam.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The capabilities of Large Language Models (LLMs) to synthesize texts that imitate human language have increased rapidly. While many people adopt this technology, the potential harm caused through texts synthesized by machines is not fully assessed. Factual errors due to model hallucinations are especially impactful in media like news articles, which serve an important function in society. Therefore, users require support in detecting LLM-generation to decrease risks posed by machine text synthesis. For this purpose, we propose the tool unCover based on explainable linguistic analysis. The tool analyzes texts through stylometric writing style analysis for grammatical information and topic modeling for semantic information. Its stylometry is based on character, word and syntactic trigrams. By inspecting the proposed techniques, the differences in LLM-generated texts can be uncovered. These findings are used to explain how text synthesis can be detected. unCover’s result is presented as a classification and visualization of the analysis. The final classification achieved an accuracy of 77.56 This is comparable to state-of-the-art products that detect LLMs while remaining technically explainable. German news articles are classified with 66.45 The visualization supports the decision of the tool and can help users navigate complex texts. These promising results show that unCover addresses challenges posed by AI content with new solutions. This is a step towards safely integrating LLMs into various areas of society.

Förderung

  • Universität Potsdam

Zitieren

APA

Liebe, L., Baum, J., Barz-Cech, T., Scheibel, W., & Döllner, J. (2026). Detecting and Comparing LLM Capabilities to Human Writers Through Linguistic Analysis. SN Computer Science, 7(6). https://doi.org/10.1007/s42979-026-05131-0

Vancouver

Liebe L, Baum J, Barz-Cech T, Scheibel W, Döllner J. Detecting and Comparing LLM Capabilities to Human Writers Through Linguistic Analysis. SN Computer Science. 2026;7(6). doi:10.1007/s42979-026-05131-0

BibTeX
@article{Liebe2026,
  author = {Liebe, Lucas and Baum, Jannis and Barz-Cech, Tim and Scheibel, Willy and Döllner, Jürgen},
  title = {Detecting and Comparing LLM Capabilities to Human Writers Through Linguistic Analysis},
  journal = {SN Computer Science},
  year = {2026},
  volume = {7},
  number = {6},
  doi = {10.1007/s42979-026-05131-0}
}
Kostenlos starten →