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

Ondrej Kobza, David Herel, Jan Cuhel, Tommaso Gargiani, Jan Pichl, Petr Marek, Jakub Konrad and Jan Sedivy ()
Additional contact information
Ondrej Kobza: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic
David Herel: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic
Jan Cuhel: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic
Tommaso Gargiani: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic
Jan Pichl: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic
Petr Marek: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic
Jakub Konrad: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic
Jan Sedivy: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic

Future Internet, 2023, vol. 15, issue 12, 1-15

Abstract: 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.

Keywords: BlenderBot; ChatBot; DeBERTa; LLM; Transformer (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/15/12/384/pdf (application/pdf)
https://www.mdpi.com/1999-5903/15/12/384/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:15:y:2023:i:12:p:384-:d:1289522

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().