Decision support systems

Context-aware decision support based on augmented intelligence with large language models

A. V. Smirnov^a, A. V. Ponomarev^a, N. G. Shilov^a, A. A. Agafonov<sup>b

a</sup> St. Petersburg Federal Research Center of the Russian Academy of Sciences
^b St. Petersburg Institute for Informatics and Automation of RAS

Abstract: Recent advancements in artificial intelligence have facilitated new forms of human-AI interaction, often referred to as augmented intelligence, where human cognitive capabilities are enhanced through various AI tools while goal-setting, coordination, and control remain human responsibilities.The article presents an original approach combining conversational, generative, and evaluative types of AI. The distinctive features of this approach include the integration and mutual enrichment of datadriven, knowledge-based, and model-oriented methods, along with the use of large language models as a means of facilitating human-system interaction during the decision-making process. The proposed approach is demonstrated through a case study of joint choice problem (schedule coordination).

Keywords: decision support systems, conversational AI, generative AI, evaluative AI, collaborative systems.

DOI: 10.14357/20718594250401

Bibliographic databases:

•