LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models

2025/04/01 by Sameer Sadruddin, Sadruddin, Sameer, Jennifer D’Souza +16 · 3 citations
Materials Science · Biochemistry, Genetics and Molecular Biology · Decision Sciences · #Machine Learning in Materials Science #Biomedical Text Mining and Ontologies #Scientific Computing and Data Management

paper · pdf · doi:10.48550/arxiv.2504.00752

Abstract

Extracting structured information from unstructured text is crucial for modeling real-world processes, but traditional schema mining relies on semi-structured data, limiting scalability. This paper introduces schema-miner, a novel tool that combines large language models with human feedback to automate and refine schema extraction. Through an iterative workflow, it organizes properties from text, incorporates expert input, and integrates domain-specific ontologies for semantic depth. Applied to materials science--specifically atomic layer deposition--schema-miner demonstrates that expert-guided LLMs generate semantically rich schemas suitable for diverse real-world applications.

Cited by

• PG-HIVE: Hybrid Incremental Schema Discovery for Property Graphs
• Addressing Longstanding Challenges in Cognitive Science with Language Models
• SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions

Related

• Schema-Driven Information Extraction from Heterogeneous Tables
• SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions
• Large language models in materials science and the need for open-source approaches
• Are LLMs Ready for Real-World Materials Discovery?
• Large language models for knowledge graph extraction from tables in materials science