Abstract
In this paper, we present a system for augmenting virtual AI characters with long-term memory, enabling them to remember facts about themselves, their world, and past experiences. We propose a memory-creation pipeline that converts raw text into condensed memories and a memory-retrieval system that utilizes these memories to generate character responses. Using a fact-checking pipeline based on GPT-4, our evaluation demonstrates that the character responses are grounded in the retrieved memories and maintain factual accuracy. We discuss the implications of our system for creating engaging and consistent virtual characters and highlight areas for future research, including large language model (LLM) guardrailing and virtual character personality development.- Anthology ID:
- 2023.inlg-main.17
- Volume:
- Proceedings of the 16th International Natural Language Generation Conference
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czechia
- Editors:
- C. Maria Keet, Hung-Yi Lee, Sina Zarrieß
- Venues:
- INLG | SIGDIAL
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 237–252
- Language:
- URL:
- https://aclanthology.org/2023.inlg-main.17
- DOI:
- 10.18653/v1/2023.inlg-main.17
- Cite (ACL):
- Fabian Landwehr, Erika Varis Doggett, and Romann M. Weber. 2023. Memories for Virtual AI Characters. In Proceedings of the 16th International Natural Language Generation Conference, pages 237–252, Prague, Czechia. Association for Computational Linguistics.
- Cite (Informal):
- Memories for Virtual AI Characters (Landwehr et al., INLG-SIGDIAL 2023)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/2023.inlg-main.17.pdf