Publishing FAIR and Machine-actionable Reviews in Materials Science: The Case for Symbolic Knowledge in Neuro-symbolic Artificial Intelligence

2026-01-08

arXiv.org

AI Summary

This work addresses the challenge of inefficient reuse of review knowledge in materials science, which is typically encoded in unstructured text and static tables. Focusing on atomic layer deposition and etching (ALD/E), the study transforms review tables into structured, FAIR-compliant knowledge published in the Open Research Knowledge Graph (ORKG). It introduces a novel neuro-symbolic AI system that employs a human-curated symbolic knowledge layer as a reliable backbone, with large language models serving only as auxiliary interfaces for symbol grounding. The approach demonstrates the critical role of symbolic methods in ensuring knowledge reliability and interpretability. The resulting resource enables queryable and reusable domain knowledge, establishing a new paradigm for synergistic neuro-symbolic integration in scientific knowledge representation.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Scientific reviews are central to knowledge integration in materials science, yet their key insights remain locked in narrative text and static PDF tables, limiting reuse by humans and machines alike. This article presents a case study in atomic layer deposition and etching (ALD/E) where we publish review tables as FAIR, machine-actionable comparisons in the Open Research Knowledge Graph (ORKG), turning them into structured, queryable knowledge. Building on this, we contrast symbolic querying over ORKG with large language model-based querying, and argue that a curated symbolic layer should remain the backbone of reliable neurosymbolic AI in materials science, with LLMs serving as complementary, symbolically grounded interfaces rather than standalone sources of truth.

Problem

• FAIR data
• machine-actionable knowledge
• scientific reviews
• materials science
• knowledge representation

Innovation

• FAIR data
• neuro-symbolic AI
• knowledge graph
• machine-actionable reviews
• symbolic knowledge