Gosia Lazuka, Andreea Simona Anghel, et al.
SC 2024
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 knowledge extraction. By applying prompt engineering with in-context learning (ICL) to a set of open-source LLMs, we demonstrate that LLMs can retrieve chemical knowledge 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 knowledge 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.
Gosia Lazuka, Andreea Simona Anghel, et al.
SC 2024
Kristjan Greenewald, Yuancheng Yu, et al.
NeurIPS 2024
Valeria de Paiva, Dario Augusto Borges Oliveira, et al.
eScience 2014
Robert Farrell, Rajarshi Das, et al.
AAAI-SS 2010