Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature
Viviane Torres da Silva, Alexandre Rademaker, Krystelle Lionti, Ronaldo Giro, Geisa Lima, Sandro Fiorini, Marcelo Archanjo, Breno W. Carvalho, Rodrigo Neumann, Anaximandro Souza, João Pedro Souza, Gabriela de Valnisio, Carmen Nilda Paz, Renato Cerqueira, Mathias Steiner
TL;DR
A Knowledge Extraction Pipeline (KEP) is introduced that automatizes LLM-assisted paragraph classification and information extraction and demonstrates that LLMs can retrieve chemical information from PDF documents, without the need for fine-tuning or training and at a reduced risk of hallucination.
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.