Generative AI Can Be Creative Too

Pulin Agrawal, Arpan Yagnik, Daqi Dong

Abstract: Large Language Models (LLMs) have significantly influenced everyday computational tasks and the pursuit of Artificial General Intelligence (AGI). However, their creativity is limited by the conventional data they learn from, particularly lacking in novelty. To enhance creativity in LLMs, this paper introduces an innovative approach using the Learning Intelligent Decision Agent (LIDA) cognitive architecture. We describe and implement a multimodal vector embeddings-based LIDA in this paper. A LIDA agent from this implementation is used to demonstrate our proposition to make generative AI more creative, specifically making it more novel. By leveraging episodic memory and attention, the LIDA-based agent can relate memories of recent unrelated events to solve current problems with novelty. Our approach incorporates a neuro-symbolic implementation of a LIDA agent that assists in generating creative ideas while illuminating a prompting technique for LLMs to make them more creative. Comparing responses from a baseline LLM and our LIDA-enhanced agent indicates an improvement in the novelty of the ideas generated.