CoHManD

CoHManD combines a locally hosted multimodal Large Language Model with a domain-specific Linked Data model. Content quality is ensured using techniques such as contextual prompts grounded in the knowledge base, Chain-of-Thought reasoning, and tailored safeguards against misleading or nonsensical outputs. Stakeholder-centered methods, including focus groups, are used to identify task demands and communication requirements. System performance is evaluated in empirical studies examining information perception, mental load, and communication efficiency in various interaction scenarios. CoHManD ensures robust, context-sensitive human–machine interaction even under incomplete or noisy data, substantially mitigating hallucinations in decision support. The system emphasizes mutual understanding by translating technical data into accessible formats and interpreting informal human input into precise machine-readable instructions. By mediating communication between humans and machines, CoHManD results in a validated framework for usable, cognitively efficient, and trustworthy human–machine communication on future construction sites.

Further information can be found on the homepage: www.exc-care.com

Duration of the Project

January 2026 until December 2027

Researchers

Carsten Kamp (kamp@ip.rwth-aachen.de)

Funding

The project is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy – EXC 3115 – 533767731

Project Partners