Domain Models are abstract representations of selected elements in a domain that is created in a collaborative process between domain and modeler experts. To achieve the creation of domain models, participants share domain knowledge to conceptualize and reason about the elements that will constitute the model. Through this exchange, a comprehensive and accurate representation of the domain is achieved, ensuring that the model effectively captures the relevant aspects and relationships within the domain. Research in Artificial Intelligence (AI) has explored various methods to assist users in the creation of domain models from textual descriptions using Natural Language Processing (NLP) and Machine Learning (ML). Recent advancements with Large Language Models (LLMs) have shown that it is possible to create domain models from text descriptions using prompting techniques; however, the generated domain models contain errors and remain constrained by the performance of the LLM used.

Despite of the impressive capabilities of LLMs to create domain models, it is evident that it does not address the needs of domain and modelers experts that participate in the creation of domain models. Every AI technique has its advantages and limitations that must be integrated with human feedback in a collaboration process. Therefore, we propose an approach that incorporates an effective human-AI collaboration supported by AI assistants that follows a dialogue approach to understand the users needs and purpose in order to suggest relevant models. Our proposal combines symbolic and subsymbolic AI techniques with explainability and traceability of the modeling decisions that assist to create domain models that are relevant for the users.