Alquist 5.0: Dialogue Trees Meet Generative Models, a Novel Approach for Enhancing SocialBot Conversations

Ondrej Kobza (), David Herel, Jan Cuhel, Tommaso Gargiani, Petr Marek and Jan Sedivy ()
Additional contact information
Ondrej Kobza: Faculty of Electrical Engineering, Czech Technical University in Prague, Jugoslávských partyzánů 1580, 160 00 Praha, Czech Republic
David Herel: Faculty of Electrical Engineering, Czech Technical University in Prague, Jugoslávských partyzánů 1580, 160 00 Praha, Czech Republic
Jan Cuhel: Faculty of Electrical Engineering, Czech Technical University in Prague, Jugoslávských partyzánů 1580, 160 00 Praha, Czech Republic
Tommaso Gargiani: Faculty of Electrical Engineering, Czech Technical University in Prague, Jugoslávských partyzánů 1580, 160 00 Praha, Czech Republic
Petr Marek: Faculty of Electrical Engineering, Czech Technical University in Prague, Jugoslávských partyzánů 1580, 160 00 Praha, Czech Republic
Jan Sedivy: Faculty of Electrical Engineering, Czech Technical University in Prague, Jugoslávských partyzánů 1580, 160 00 Praha, Czech Republic

Future Internet, 2024, vol. 16, issue 9, 1-28

Abstract: This article introduces Alquist 5.0, our SocialBot that was designed for the Alexa Prize SocialBot Grand Challenge 5. Building upon previous iterations, we present the integration of our novel neural response generator (NRG) Barista within a hybrid architecture that combines traditional predefined dialogues with advanced neural response generation. We provide a comprehensive analysis of the current state-of-the-art NRGs and large language models (LLMs), leveraging these insights to enhance Barista’s capabilities. A key focus of our development was in ensuring the safety of our chatbot and implementing robust measures to prevent profanity and inappropriate content. Additionally, we incorporated a new search engine to improve information retrieval and response accuracy. Expanding the capabilities of our system, we designed Alquist 5.0 to accommodate multimodal devices, utilizing APL templates enriched with custom features to deliver an outstanding conversational experience complemented by an excellent user interface. This paper offers detailed insights into the development of Alquist 5.0, which effectively addresses evolving user demands while preserving its empathetic and knowledgeable conversational prowess across a wide range of topics.

Keywords: Alexa Prize; SocialBot; neural response generator; Barista; hybrid dialogues; safety; Vicuna; BlenderBot 3 (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/16/9/344/pdf (application/pdf)
https://www.mdpi.com/1999-5903/16/9/344/ (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:16:y:2024:i:9:p:344-:d:1482485

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 ().