ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literature

TL;DR

ComProScanner is a multi-agent framework that automates the extraction, validation, and visualization of complex chemical composition and property data from scientific literature, enhancing dataset creation for machine learning applications.

Contribution

It introduces a novel multi-agent platform that streamlines the extraction and validation of structured chemical data from scientific articles, integrating synthesis data for comprehensive database development.

Findings

DeepSeek-V3-0324 achieved 0.82 accuracy in extraction tasks.

Framework outperforms existing models in extracting complex chemical data.

Provides a user-friendly tool for building datasets from literature.

Abstract

Since the advent of various pre-trained large language models, extracting structured knowledge from scientific text has experienced a revolutionary change compared with traditional machine learning or natural language processing techniques. Despite these advances, accessible automated tools that allow users to construct, validate, and visualise datasets from scientific literature extraction remain scarce. We therefore developed ComProScanner, an autonomous multi-agent platform that facilitates the extraction, validation, classification, and visualisation of machine-readable chemical compositions and properties, integrated with synthesis data from journal articles for comprehensive database creation. We evaluated our framework using 100 journal articles against 10 different LLMs, including both open-source and proprietary models, to extract highly complex compositions associated with ceramic piezoelectric materials and corresponding piezoelectric strain coefficients (d33), motivated by the lack of a large dataset for such materials. DeepSeek-V3-0324 outperformed all models with a significant overall accuracy of 0.82. This framework provides a simple, user-friendly, readily-usable package for extracting highly complex experimental data buried in the literature to build machine learning or deep learning datasets.