An Open-Domain Avatar Chatbot by Exploiting a Large Language Model
Takato Yamazaki, Tomoya Mizumoto, Katsumasa Yoshikawa, Masaya Ohagi, Toshiki Kawamoto, Toshinori Sato
Abstract
With the ambition to create avatars capable of human-level casual conversation, we developed an open-domain avatar chatbot, situated in a virtual reality environment, that employs a large language model (LLM). Introducing the LLM posed several challenges for multimodal integration, such as developing techniques to align diverse outputs and avatar control, as well as addressing the issue of slow generation speed. To address these challenges, we integrated various external modules into our system. Our system is based on the award-winning model from the Dialogue System Live Competition 5. Through this work, we hope to stimulate discussions within the research community about the potential and challenges of multimodal dialogue systems enhanced with LLMs.- Anthology ID:
- 2023.sigdial-1.40
- Volume:
- Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czechia
- Editors:
- Svetlana Stoyanchev, Shafiq Joty, David Schlangen, Ondrej Dusek, Casey Kennington, Malihe Alikhani
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 428–432
- Language:
- URL:
- https://aclanthology.org/2023.sigdial-1.40
- DOI:
- 10.18653/v1/2023.sigdial-1.40
- Cite (ACL):
- Takato Yamazaki, Tomoya Mizumoto, Katsumasa Yoshikawa, Masaya Ohagi, Toshiki Kawamoto, and Toshinori Sato. 2023. An Open-Domain Avatar Chatbot by Exploiting a Large Language Model. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 428–432, Prague, Czechia. Association for Computational Linguistics.
- Cite (Informal):
- An Open-Domain Avatar Chatbot by Exploiting a Large Language Model (Yamazaki et al., SIGDIAL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.sigdial-1.40.pdf