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

arXiv: https://arxiv.org/abs/2504.00752 · HTML: https://mlsanity.com/paper/2504.00752/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 44 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Transformer models: an introduction and catalog](https://mlsanity.com/paper/2302.07730/) (2023)
- [ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction](https://mlsanity.com/paper/2310.12537/) (2023)
- [Entity Type Prediction Leveraging Graph Walks and Entity Descriptions](https://mlsanity.com/paper/2207.14094/) (2022)
- [Schema-adaptable Knowledge Graph Construction](https://mlsanity.com/paper/2305.08703/) (2023)
- [Large Language Models for JSON Schema Discovery](https://mlsanity.com/paper/2407.03286/) (2024)
- [The landscape of ontologies in materials science and engineering: A survey and evaluation](https://mlsanity.com/paper/2408.06034/) (2024)
- [StaTIX - Statistical Type Inference on Linked Data](https://mlsanity.com/paper/1902.00490/) (2019)

## Built on by (most cited first, 9 of 9)

- [Retrieval-Augmented Generation of Ontologies from Relational Databases](https://mlsanity.com/paper/2506.01232/) (2025)
- [Addressing Longstanding Challenges in Cognitive Science with Language Models](https://mlsanity.com/paper/2511.00206/) (2025)
- [Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis](https://mlsanity.com/paper/2602.10881/) (2026)
- [From Automation to Collaboration: Human-in-the-Loop Methods for Safe and Trustworthy NLP](https://mlsanity.com/paper/2605.25226/) (2026)
- [Generative Ontology Induction: Domain-Agnostic Schema Discovery from Document Corpora Using Large Language Models](https://mlsanity.com/paper/2607.16201/) (2026)
- [SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions](https://mlsanity.com/paper/2607.27955/) (2026)
- [Mined from Scientific Literature: Process Schemas for Atomic Layer Deposition and Etching in Materials Science](https://mlsanity.com/paper/2609.12139/) (2026)
- [Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal Research](https://mlsanity.com/paper/2609.22209/) (2026)
- [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026)

## Abstract (arXiv)

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.