Articles publicats

Articles publicats 1 registres trobats  La cerca s'ha fet en 0.01 segons. 
1.
10 p, 413.0 KB Systematic testing of three Language Models reveals low language accuracy, absence of response stability, and a yes-response bias / Dentella, Vittoria (Universitat Rovira i Virgili. Departament d'Estudis Anglesos i Alemanys) ; Günther, Fritz (Humboldt-Universitat zu Berlin. Institut für Psychologie) ; Leivada, Evelina (Universitat Autònoma de Barcelona. Departament de Filologia Catalana)
Humans are universally good in providing stable and accurate judgments about what forms part of their language and what not. Large Language Models (LMs) are claimed to possess human-like language abilities; hence, they are expected to emulate this behavior by providing both stable and accurate answers, when asked whether a string of words complies with or deviates from their next-word predictions. [...]
2023 - 10.1073/pnas.2309583120
Proceedings of the National Academy of Sciences of the United States of America, Vol. 120 Núm. 51 (2023) , p. e2309583120  

Us interessa rebre alertes sobre nous resultats d'aquesta cerca?
Definiu una alerta personal via correu electrònic o subscribiu-vos al canal RSS.