• Projects

• Research Area 1

P2 | Interfaces: Implementing user-centered ComAI

• Prof. Dr. Rainer Malaka

With the rise of Large Language Models (LLMs) and their adaptation to human-computer communication based on human feedback, users are increasingly expecting human-like interaction from ComAIs.

However, these models designed specifically for human-computer communication face mainly two problems: First, they rely only on the data they are trained with, which is often biased and insufficient.

Second, they are only created to produce text and responses, but there is no validation of the truthfulness of the generated output during the training. Therefore, when designing and building ComAIs, it is important that users know that such problems are a feature of LLMs. Interfaces are crucial in helping users to identify problematic information and evaluate the data sources’ quality and reliability.

Against this background, P2 uses the example of conversational bots to examine the design and implementation of ComAI interfaces as a dimension of their sociomaterial constitution. Investigating both the conversational and paralinguistic features of interfaces, we research which implementation features of the interface design influence user-alignment and how.

PUBLICATIONS:

• Beßler, D., Porzel, R., Pomarlan, M., Vyas, A., Höffner, S., Beetz, M., Malaka, R., & Bateman, J. (2020, November 24). Foundations of the Socio-physical Model of Activities (SOMA) for Autonomous Robotic Agents. https://arxiv.org/abs/2011.11972v1
• Bonfert, M., Zargham, N., Saade, F., Porzel, R., & Malaka, R. (2021). An Evaluation of Visual Embodiment for Voice Assistants on Smart Displays. CUI 2021 – 3rd Conference on Conversational User Interfaces. https://doi.org/10.1145/3469595.3469611
• Höffner, S., Porzel, R., Hedblom, M. M., Pomarlan, M., Cangalovic, V. S., Pfau, J., Bateman, J. A., & Malaka, R. (2022). Deep understanding of everyday activity commands for household robots. Semantic Web. https://doi.org/10.3233/SW-222973
• Malaka, R., & Zipf, A. (2000). DEEP MAP: Challenging IT Research In The Framework Of A Tourist Information System. In D. R. Fesenmaier, S. Klein, & D. Buhalis (Eds.), Information and Communication Technologies in Tourism 2000 (pp. 15–27). Springer. https://doi.org/10.1007/978-3-7091-6291-0_2
• Reicherts, L., Zargham, N., Bonfert, M., Rogers, Y., & Malaka, R. (2021). May I Interrupt? Diverging Opinions on Proactive Smart Speakers. Proceedings of the 3rd Conference on Conversational User Interfaces, 1–10. https://doi.org/10.1145/3469595.3469629
• Runge, N., Samsonov, P., Degraen, D., & Schöning, J. (2016). No more Autobahn! Scenic Route Generation Using Googles Street View. Proc. of the International Conference on Intelligent User Interfaces, https://doi.org/10.1145/2856767.2856804
• Spillner, L., & Wenig, N. (2021). Talk to Me on My Level – Linguistic Alignment for Chatbots. Proceedings of the 23rd International Conference on Mobile Human-Computer Interaction, 1–12. https://doi.org/10.1145/3447526.3472050
• Zargham, N., Avanesi, V., Reicherts, L., Scott, A. E., Rogers, Y., & Malaka, R. (2023). “Funny How?” A Serious Look at Humor in Conversational Agents. Proceedings of the 5th International Conference on Conversational User Interfaces, 1–7. https://doi.org/10.1145/3571884.3603761

• Zargham, N., Bonfert, M., Porzel, R., Doring, T., & Malaka, R. (2021). Multi-Agent Voice Assistants: An Investigation of User Experience. 20th International Conference on Mobile and Ubiquitous Multimedia, 98–107. https://doi.org/10.1145/3490632.3490662
• Zargham, N., Reicherts, L., Bonfert, M., Voelkel, S. T., Schoening, J., Malaka, R., & Rogers, Y. (2022). Understanding circumstances for desirable proactive behaviour of voice assistants: The proactivity dilemma. Proceedings of the 4th Conference on Conversational User Interfaces. https://doi.org/10.1145/3543829.3543834