fig2

LLM-driven materials knowledge extraction: multimodal parsing, ontology, and agentic systems

Figure 2. Materials knowledge extraction as a PCA framework. Perception parses raw PDF literature; cognition supplies ontology and knowledge-graph grounding; action converts evidence into structured records through schema-based, schema-free, or agentic extraction. Quality control connects all stages through source provenance, ontology constraints, physical checks, and feedback loops. PCA: Perception–Cognition–Action; AI: artificial intelligence; QC: quality control; KG: knowledge graph.

Journal of Materials Informatics
ISSN 2770-372X (Online)
Follow Us

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/