Document Type
Article
Abstract
Temporal alignment in stateful generative artificial intelligence (AI) systems remains an underexplored area, particularly beyond goal-driven approaches in planning. Stateful refers to maintaining a persistent memory or “state” across runs or sessions. This helps with referencing past information to make system outputs more contextual and relevant. This position paper proposes a framework for temporal alignment with several configurable toggles. We present four alignment mechanisms: knowledge graph path-based, neural score-based, vector similarity-based, and sequential process-guided alignment. By offering these interchangeable approaches, we aim to provide a flexible solution adaptable to complex and real-world applications. This paper discusses the potential benefits and challenges of each alignment method and positions the importance of a configurable system in advancing progress in stateful generative AI systems.
Publication Info
Preprint version 2024.
APA Citation
Roy, K., Zi, Y., & Sheth, A. (2024). Towards pragmatic temporal alignment in stateful generative AI systems: A configurable approach. [Preprint]
Rights
© 2024, The Authors
