Publications

@inproceedings{hafner_leveraging_2025,

title = {Leveraging Virtual Prototypes for Training Data Collection in LLM-Based Voice User Interface Development for Machines},

author = {P. Häfner and F. Eisenlohr and A. Karande and M. Grethler and A. Mukherjee and N. Tran},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105000344182&doi=10.1109%2fAIxVR63409.2025.00054&partnerID=40&md5=05fe014eddba395881575bec5d96ce15},

doi = {10.1109/AIxVR63409.2025.00054},

isbn = {979-833152157-8 (ISBN)},

year  = {2025},

date = {2025-01-01},

booktitle = {Proc. - IEEE Int. Conf. Artif. Intell. Ext. Virtual Real., AIxVR},

pages = {281–285},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Voice User Interfaces (VUIs) are becoming increasingly valuable in industrial applications, offering hands-free control in complex environments. However, developing and validating VUIs for such applications faces challenges, including limited access to physical prototypes and high testing costs. This paper presents a methodology that utilizes virtual reality (VR) prototypes to collect training data for large language model (LLM)-based VUIs, allowing early-stage voice control development before physical prototypes are accessible. Through an immersive Wizard-of-Oz (WoZ) method, participants interact with a virtual reality representation of a machine, generating realistic, scenario-based conversational data. This combined WoZ and VR approach enables high-quality data collection and iterative model training, offering an effective solution that can be applied across various types of machine. Preliminary findings demonstrate the viability of VR in generating diverse and robust data sets that closely simulate real-world dialogs for voice interactions in industrial settings. © 2025 IEEE.},

keywords = {Artificial intelligence, Behavioral Research, Data collection, Language Model, Large language model, large language models, Model-based OPC, Training data, User interface development, Virtual environments, Virtual Prototype, Virtual Prototyping, Virtual Reality, Voice User Interface, Voice User Interfaces, Wizard of Oz, Wizard-of-Oz Method},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manesh_how_2024,

title = {How People Prompt Generative AI to Create Interactive VR Scenes},

author = {S. A. Manesh and T. Zhang and Y. Onishi and K. Hara and S. Bateman and J. Li and A. Tang},

editor = {Vallgarda A. and Jonsson L. and Fritsch J. and Alaoui S.F. and Le Dantec C.A.},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85200348302&doi=10.1145%2f3643834.3661547&partnerID=40&md5=11831bb65214fd75905ccdaeb8356cdf},

doi = {10.1145/3643834.3661547},

isbn = {979-840070583-0 (ISBN)},

year  = {2024},

date = {2024-01-01},

booktitle = {Proc. ACM Des. Interact. Syst. Conf.},

pages = {2319–2340},

publisher = {Association for Computing Machinery, Inc},

abstract = {Generative AI tools can provide people with the ability to create virtual environments and scenes with natural language prompts. Yet, how people will formulate such prompts is unclear—particularly when they inhabit the environment that they are designing. For instance, it is likely that a person might say, “Put a chair here,” while pointing at a location. If such linguistic and embodied features are common to people’s prompts, we need to tune models to accommodate them. In this work, we present a Wizard of Oz elicitation study with 22 participants, where we studied people’s implicit expectations when verbally prompting such programming agents to create interactive VR scenes. Our fndings show when people prompted the agent, they had several implicit expectations of these agents: (1) they should have an embodied knowledge of the environment; (2) they should understand embodied prompts by users; (3) they should recall previous states of the scene and the conversation, and that (4) they should have a commonsense understanding of objects in the scene. Further, we found that participants prompted diferently when they were prompting in situ (i.e. within the VR environment) versus ex situ (i.e. viewing the VR environment from the outside). To explore how these lessons could be applied, we designed and built Ostaad, a conversational programming agent that allows non-programmers to design interactive VR experiences that they inhabit. Based on these explorations, we outline new opportunities and challenges for conversational programming agents that create VR environments. © 2024 Copyright held by the owner/author(s).},

keywords = {Embodied interaction, Embodied knowledge, Embodied prompting, Generative AI, Interactive virtual reality, Multi-modal, Natural languages, Programming agents, Prompting, User interfaces, Virtual Reality, Wizard of Oz},

pubstate = {published},

tppubtype = {inproceedings}

}