EUVIMEDEUVIMED entdecken
Crossref

An Information-Theoretic Approach for Detecting Edits in AI-Generated Text

Idan Kashtan, Alon Kipnis

Harvard Data Science Review · 08.11.2024 · (Special Issue 5)

DOI: 10.1162/99608f92.5dbf3265 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Harvard Data Science Review, online erschienen am 08.11.2024. Verfasst von Idan Kashtan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a method to determine whether a given article was written entirely by a generative language model or perhaps contains edits by a different author, possibly a human. Our process involves multiple tests for the origin of individual sentences or other pieces of text and combining these tests using a method that is sensitive to rare alternatives, i.e., non-null effects are few and scattered across the text in unknown locations. Interestingly, this method also identifies pieces of text suspected to contain edits. We demonstrate the effectiveness of the method in detecting edits through extensive evaluations using real data and provide an information-theoretic analysis of the factors affecting its success. In particular, we discuss optimality properties under a theoretical framework for text editing saying that sentences are generated mainly by the language model, except perhaps for a few sentences that might have originated via a different mechanism. Our analysis raises several interesting research questions at the intersection of information theory and data science.

Zitieren

APA

Kashtan, I., & Kipnis, A. (2024). An Information-Theoretic Approach for Detecting Edits in AI-Generated Text. Harvard Data Science Review. https://doi.org/10.1162/99608f92.5dbf3265

Vancouver

Kashtan I, Kipnis A. An Information-Theoretic Approach for Detecting Edits in AI-Generated Text. Harvard Data Science Review. 2024. doi:10.1162/99608f92.5dbf3265

BibTeX
@article{Kashtan2024,
  author = {Kashtan, Idan and Kipnis, Alon},
  title = {An Information-Theoretic Approach for Detecting Edits in AI-Generated Text},
  journal = {Harvard Data Science Review},
  year = {2024},
  number = {Special Issue 5},
  doi = {10.1162/99608f92.5dbf3265}
}
Kostenlos starten →