Extending Logical Neural Networks using First-Order Theories
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Logical Neural Networks (LNNs) are a type of architecture which combine a neural network's abilities to learn and systems of formal logic's abilities to perform symbolic reasoning. LLNs provide programmers the ability to implicitly modify the underlying structure of the neural network via logical formulae. In this paper, we take advantage of this abstraction to extend LNNs to support equality and function symbols via first-order theories. This extension improves the power of LNNs by significantly increasing the types of problems they can tackle. As a proof of concept, we add support for the first-order theory of equality to IBM's LNN library and demonstrate how the introduction of this allows the LNN library to now reason about expressions without needing to make the unique-names assumption.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 2 of its 4 references that are in the map. First posted on arXiv 6 Jul 2022.
Builds on
2 of 4 references.
References · 2
- 2020Logical Neural Networkscited by 119
- 2018Can Neural Networks Understand Logical Entailment?cited by 24
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning
- 2025Standard Neural Computation Alone Is Insufficient for Logical Intelligence
- 2022Evaluating Step-by-Step Reasoning through Symbolic Verification
- 2025On the Limits of Hierarchically Embedded Logic in Classical Neural Networks
- 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
- 2026The Emergent Symbolic Structure of Artificial Neural Networks
- 2023COOL: A Constraint Object-Oriented Logic Programming Language and its Neural-Symbolic Compilation System
- 2024Neuro-symbolic Learning Yielding Logical Constraints