Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language
This addresses the challenge of making neuro-symbolic modeling accessible to non-experts, though it is incremental as it builds on existing frameworks like DomiKnowS.
The paper tackles the problem of enabling domain experts to create neuro-symbolic models without ML/AI expertise by developing a conversational pipeline that uses natural language prompts to generate declarative programs in the DomiKnowS framework, resulting in a system that allows users to formally declare knowledge for customized neural models.
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.