Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Faghihi, Hossein Rajaby, Nafar, Aliakbar, Uszok, Andrzej, Karimian, Hamid, Kordjamshidi, Parisa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929441611972608
author Faghihi, Hossein Rajaby
Nafar, Aliakbar
Uszok, Andrzej
Karimian, Hamid
Kordjamshidi, Parisa
author_facet Faghihi, Hossein Rajaby
Nafar, Aliakbar
Uszok, Andrzej
Karimian, Hamid
Kordjamshidi, Parisa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20513
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language
Faghihi, Hossein Rajaby
Nafar, Aliakbar
Uszok, Andrzej
Karimian, Hamid
Kordjamshidi, Parisa
Computation and Language
Artificial Intelligence
Human-Computer Interaction
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.
title Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2407.20513