[Submitted on 30 Jul 2024]
View a PDF of the paper titled Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language, by Hossein Rajaby Faghihi and 4 other authors
Abstract: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.
Submission history
From: Hossein Rajaby Faghihi [view email]
[v1]
Tue, 30 Jul 2024 03:10:30 UTC (7,735 KB)
Source link
lol
