Retaining Expert Knowledge with ML


For a long time, and still today, human capital in the form of human knowledge and intelligence has been considered one of the crucial key resources for innovation, substantially driving the success of a company. In addition, artificial intelligence (AI), i.e., machines that exhibit aspects of human intelligence, is becoming another important source of innovation alongside humans as the sole driver. In contrast, however, humans still have a clear advantage, especially in more complex and knowledge-intensive tasks that require a high degree of emotional intelligence, intuition, creative thinking as well as an experiential and contextual interaction. In order to address this field of tension, the research area of human-computer interaction (HCI) is increasingly concerned with hybrid forms of collaboration between humans and machines.

However, human-machine collaboration in particular poses a special challenge, since knowledge structures of humans differ substantially from those of machines. But it is exactly this human knowledge that represents a decisive key resource of companies, which must be both preserved and expanded. The term “knowledge” can refer to a theoretical or practical understanding of a subject, which can be implicit (as with practical skill or expertise) or explicit (as with the theoretical understanding of a subject).

The aim of this project is to explore the possibilities of knowledge preservation and utilization at the intersection of humans and machines by means of decision support systems (besides conventional knowledge management systems) at the interface of the disciplines knowledge management, artificial intelligence and human-computer interaction.




01.02.2022 - 31.07.2025


Involved DSI Researchers

Philipp Spitzer


Journal Articles
The Impact of Imperfect XAI on Human-AI Decision-Making
Morrison, K.; Spitzer, P.; Turri, V.; Feng, M.; Kühl, N.; Perer, A.
2024. Proceedings of the ACM on human-computer interaction
Journal Articles
ML-Based Teaching Systems: A Conceptual Framework
Spitzer, P.; Kühl, N.; Heinz, D.; Satzger, G.
2023. Proceedings of the ACM on Human-Computer Interaction, 7 (CSCW2), Art.-Nr.: 348. doi:10.1145/3610197
Conference Papers
On the Perception of Difficulty: Differences between Humans and AI
Spitzer, P.; Holstein, J.; Vössing, M.; Kühl, N.
2023. AutomationXP23: Intervening, Teaming, Delegating Creating Engaging Automation Experiences, doi:10.48550/arXiv.2304.09803
ML-Based Teaching Systems: A Conceptual Framework
Spitzer, P.; Kühl, N.; Heinz, D.; Satzger, G.
2023. doi:10.5445/IR/1000158546
Conference Papers
Training Novices: The Role of Human-AI Collaboration and Knowledge Transfer
Spitzer, P.; Kühl, N.; Goutier, M.
2022. Workshop on Human-Machine Collaboration and Teaming (HM-CaT 2022), 23rd July, Baltimore. doi:10.48550/arXiv.2207.00497
Conference Papers
A New Metric for Lumpy and Intermittent Demand Forecasts: Stock-keeping-oriented Prediction Error Costs
Martin, D.; Spitzer, P.; Kühl, N.
2020. 53rd Annual Hawaii International Conference on System Sciences (HICSS-53), Grand Wailea, Maui, HI, January 7-10, 2020