Fröhling, L.; Zubiaga, A.: Feature-based detection of automated language models: Tackling GPT-2, GPT-3 and Grover. In: PeerJ Computer Science 7 (2021), e443. DOI: https://doi.org/10.7717/peerj-cs.443
Abstract: | |
The recent improvements of language models have drawn much attention to potential cases of use and abuse of automatically generated text. Great effort is put into the development of methods to detect machine generations among human-written text in order to avoid scenarios in which the large-scale generation of text with minimal cost and effort undermines the trust in human interaction and factual information online. While most of the current approaches rely on the availability of expensive language models, we propose a simple feature-based classifier for the detection problem, using carefully crafted features that attempt to model intrinsic differences between human and machine text. Our research contributes to the field in producing a detection method that achieves performance competitive with far more expensive methods, offering an accessible “first line-of-defense” against the abuse of language models. Furthermore, our experiments show that different sampling methods lead to different types of flaws in generated text. | |
License of this version: | CC BY 4.0 Unported |
Document Type: | Article |
Publishing status: | publishedVersion |
Issue Date: | 2021 |
Appears in Collections: | Wirtschaftswissenschaftliche Fakultät |
pos. | country | downloads | ||
---|---|---|---|---|
total | perc. | |||
1 | ![]() |
Germany | 10 | 47.62% |
2 | ![]() |
United States | 5 | 23.81% |
3 | ![]() |
Japan | 1 | 4.76% |
4 | ![]() |
Indonesia | 1 | 4.76% |
5 | ![]() |
Europe | 1 | 4.76% |
6 | ![]() |
Estonia | 1 | 4.76% |
7 | ![]() |
Switzerland | 1 | 4.76% |
8 | ![]() |
Austria | 1 | 4.76% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.