Memories for Virtual AI Characters

Fabian Landwehr, Erika Varis Doggett, Romann M. Weber


In Sessions:

INLG Oral Session 3: Leveraging Large Language Models for NLG: (Thursday, 10:30 CEST, Sun II , Watch on Zoom , Chat on Discord )


Memories for Virtual AI Characters

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.