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

Sameer Sadruddin, Jennifer D'Souza, Eleni Poupaki, Alex Watkins, Hamed Babaei Giglou +5 more
4/1/2025
cs.CLcs.AIcs.DL

No official code found. Best implementation: sciknoworg/schema-miner (39 stars, MIT, last commit 2026-03-23).

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.

View on arXivView PDF

Code Implementations(1)

sciknoworg/schema-minerCommunity100%
MIT

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

399Python, Jupyter NotebookDec 9, 20247 months agoMIT
human-in-the-loopjson-schema-mininglangchainlarge-language-modelsnatural-language-processing+3 more

Similar Papers

Materials science in the era of large language models: a perspective

85% match2024

Large language models in materials science and the need for open-source approaches

84% match2025

Are LLMs Ready for Real-World Materials Discovery?

83% match1 repo22024

From Text to Insight: Large Language Models for Materials Science Data Extraction

83% match2024

Foundational Large Language Models for Materials Research

83% match1 repo632024

Schema Generation for Large Knowledge Graphs Using Large Language Models

82% match2025

Cite this paper

@article{sadruddin2025llmsschemadiscovery,
  title  = {LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models},
  author = {Sameer Sadruddin and Jennifer D'Souza and Eleni Poupaki and Alex Watkins and Hamed Babaei Giglou and Anisa Rula and Bora Karasulu and Sören Auer and Adrie Mackus and Erwin Kessels},
  year   = {2025},
  eprint = {2504.00752},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.00752v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.00752.svg)](https://codeofpaper.com/paper/2504.00752)

Discussion