This paper presents a conversational pipeline for crafting domain knowledge for complex neuro-symbolic models through natural language prompts. It leverages large language models to generate declarative programs in the DomiKnowS framework. The programs in this framework express concepts and their relationships as a graph in addition to logical constraints between them. The graph, later, can be connected to trainable neural models according to those specifications. Our proposed pipeline utilizes techniques like dynamic in-context demonstration retrieval, model refinement based on feedback from a symbolic parser, visualization, and user interaction to generate the tasks' structure and formal knowledge representation. This approach empowers domain experts, even those not well-versed in ML/AI, to formally declare their knowledge to be incorporated in customized neural models in the DomiKnowS framework.
@article{arxiv.2407.20513,
title = {Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language},
author = {Hossein Rajaby Faghihi and Aliakbar Nafar and Andrzej Uszok and Hamid Karimian and Parisa Kordjamshidi},
journal= {arXiv preprint arXiv:2407.20513},
year = {2024}
}