Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature

TL;DR

This paper presents a pipeline leveraging large language models to automatically extract synthesis details of reticular materials from scientific literature, reducing manual effort and improving efficiency.

Contribution

The study introduces a Knowledge Extraction Pipeline (KEP) that uses prompt engineering with open-source LLMs for paragraph classification and information extraction without fine-tuning.

Findings

LLMs can accurately retrieve chemical information from PDFs

Few-shot in-context learning achieves high performance

The approach reduces human annotation efforts

Abstract

Automated knowledge extraction from scientific literature can potentially accelerate materials discovery. We have investigated an approach for extracting synthesis protocols for reticular materials from scientific literature using large language models (LLMs). To that end, we introduce a Knowledge Extraction Pipeline (KEP) that automatizes LLM-assisted paragraph classification and information extraction. By applying prompt engineering with in-context learning (ICL) to a set of open-source LLMs, we demonstrate that LLMs can retrieve chemical information from PDF documents, without the need for fine-tuning or training and at a reduced risk of hallucination. By comparing the performance of five open-source families of LLMs in both paragraph classification and information extraction tasks, we observe excellent model performance even if only few example paragraphs are included in the ICL prompts. The results show the potential of the KEP approach for reducing human annotations and data curation efforts in automated scientific knowledge extraction.