Grounding Methods for Neural-Symbolic AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ontiveros, Rodrigo Castellano, Giannini, Francesco, Gori, Marco, Marra, Giuseppe, Diligenti, Michelangelo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915578377142272
author Ontiveros, Rodrigo Castellano
Giannini, Francesco
Gori, Marco
Marra, Giuseppe
Diligenti, Michelangelo
author_facet Ontiveros, Rodrigo Castellano
Giannini, Francesco
Gori, Marco
Marra, Giuseppe
Diligenti, Michelangelo
contents A large class of Neural-Symbolic (NeSy) methods employs a machine learner to process the input entities, while relying on a reasoner based on First-Order Logic to represent and process more complex relationships among the entities. A fundamental role for these methods is played by the process of logic grounding, which determines the relevant substitutions for the logic rules using a (sub)set of entities. Some NeSy methods use an exhaustive derivation of all possible substitutions, preserving the full expressive power of the logic knowledge. This leads to a combinatorial explosion in the number of ground formulas to consider and, therefore, strongly limits their scalability. Other methods rely on heuristic-based selective derivations, which are generally more computationally efficient, but lack a justification and provide no guarantees of preserving the information provided to and returned by the reasoner. Taking inspiration from multi-hop symbolic reasoning, this paper proposes a parametrized family of grounding methods generalizing classic Backward Chaining. Different selections within this family allow us to obtain commonly employed grounding methods as special cases, and to control the trade-off between expressiveness and scalability of the reasoner. The experimental results show that the selection of the grounding criterion is often as important as the NeSy method itself.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Grounding Methods for Neural-Symbolic AI
Ontiveros, Rodrigo Castellano
Giannini, Francesco
Gori, Marco
Marra, Giuseppe
Diligenti, Michelangelo
Artificial Intelligence
A large class of Neural-Symbolic (NeSy) methods employs a machine learner to process the input entities, while relying on a reasoner based on First-Order Logic to represent and process more complex relationships among the entities. A fundamental role for these methods is played by the process of logic grounding, which determines the relevant substitutions for the logic rules using a (sub)set of entities. Some NeSy methods use an exhaustive derivation of all possible substitutions, preserving the full expressive power of the logic knowledge. This leads to a combinatorial explosion in the number of ground formulas to consider and, therefore, strongly limits their scalability. Other methods rely on heuristic-based selective derivations, which are generally more computationally efficient, but lack a justification and provide no guarantees of preserving the information provided to and returned by the reasoner. Taking inspiration from multi-hop symbolic reasoning, this paper proposes a parametrized family of grounding methods generalizing classic Backward Chaining. Different selections within this family allow us to obtain commonly employed grounding methods as special cases, and to control the trade-off between expressiveness and scalability of the reasoner. The experimental results show that the selection of the grounding criterion is often as important as the NeSy method itself.
title Grounding Methods for Neural-Symbolic AI
topic Artificial Intelligence
url https://arxiv.org/abs/2507.08216