Enhancements in BlenderBot 3: Expanding Beyond a Singular Model Governance and Boosting Generational Performance

Autor: Ondrej Kobza, David Herel, Jan Cuhel, Tommaso Gargiani, Jan Pichl, Petr Marek, Jakub Konrad, Jan Sedivy
Jazyk: angličtina
Rok vydání: 2023
Předmět:
Zdroj: Future Internet, Vol 15, Iss 12, p 384 (2023)
Druh dokumentu: article
ISSN: 15120384
1999-5903
DOI: 10.3390/fi15120384
Popis: This paper provides a pioneering examination and enhancement of generative chat models, with a specific focus on the BlenderBot 3 model. Through meticulous interaction with a diverse set of human participants, we dissected the fundamental components of these models, unveiling several deficiencies, including long-term memory and entity recognition. Leveraging these insights, we engineered refined, streamlined iterations, culminating in a chatbot that transcends the capabilities of all existing models. Our work follows Occam’s razor principle and proves that, for tasks with relatively low complexity, using large overparameterized models instead of smaller ones does not bring significant benefits but increases latency, which may result in a lowered overall user experience. In upholding our commitment to transparency and the progression of shared knowledge, we have made our improved model universally accessible through open-source distribution.
Databáze: Directory of Open Access Journals
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje