concept

symbolic knowledge

Also known as: symbolic knowledge base, symbolic knowledge system

Facts (14)

Sources

Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org arXiv Nov 7, 2024 5 facts

claimHooshyar et al. (2023) argue that augmenting deep neural networks with symbolic knowledge can contribute to the development of trustworthy and interpretable AI systems for education.

referenceXu et al. (2018) introduced a semantic loss function designed to integrate symbolic knowledge into deep learning models, as published in the International Conference on Machine Learning.

referenceJunyan Cheng and Peter Chin explored the transition from neural representation to symbolic knowledge in their 2023 arXiv preprint.

referenceThe 'Facts as Experts' approach, proposed by Pat Verga, Haitian Sun, Livio Baldini Soares, and William Cohen in 2021, utilizes adaptable and interpretable neural memory over symbolic knowledge.

referenceWilliam W Cohen, Haitian Sun, R Alex Hofer, and Matthew Siegler proposed scalable neural methods for reasoning with a symbolic knowledge base in a 2020 arXiv preprint.

Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org arXiv Feb 16, 2025 2 facts

claimIntegrating symbolic knowledge into neural network loss functions reinforces the connection between neural learning and symbolic reasoning in the contexts of model distillation, fine-tuning, pre-training, and transfer learning.

referencePat Verga, Haitian Sun, Livio Baldini Soares, and William W. Cohen authored 'Facts as experts: Adaptable and interpretable neural memory over symbolic knowledge', published as an arXiv preprint in 2020.

Construction of intelligent decision support systems through ... - Nature nature.com Nature Oct 10, 2025 1 fact

claimKnowledge graph embeddings integrate symbolic knowledge through statistical learning.

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv Sep 22, 2025 1 fact

claimFuture work in Knowledge Alignment and Dynamic Integration for LLM+KG systems should focus on quantifying alignment using metrics that score both semantic overlap and structural compatibility between parametric knowledge in the LLM and symbolic knowledge in the KG.

A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Springer Dec 9, 2025 1 fact

claimExplicit symbolic knowledge can compensate for limited training data by providing information that would otherwise need to be learned implicitly, which reduces overfitting and improves model robustness in data-scarce environments, as noted in citation 76.

Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org Frontiers 1 fact

claimA persistent representation gap between neural and symbolic knowledge systems creates information fusion barriers in Knowledge Graph (KG) construction, causes semantic misalignment in Large Language Model (LLM) enhancement, and poses integration difficulties in collaborative systems.

Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org arXiv 1 fact

referenceZhu et al. focus on the creation of multi-modal knowledge graphs, specifically by combining symbolic knowledge in a knowledge graph with corresponding images.

Building Trustworthy NeuroSymbolic AI Systems - arXiv arxiv.org arXiv 1 fact

claimNeuroSymbolic AI (NeSy-AI) systems integrate the approximating capabilities of neural networks with symbolic knowledge to enable abstract conceptual reasoning, extrapolation from limited data, and explainable outcomes.

Combining Knowledge Graphs and Large Language Models - arXiv arxiv.org arXiv Jul 9, 2024 1 fact

referenceKenneth Marino, Xinlei Chen, Devi Parikh, Abhinav Gupta, and Marcus Rohrbach developed 'KRISP', a method for integrating implicit and symbolic knowledge for open-domain knowledge-based visual question answering.