Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929578880008192 |
|---|---|
| author | da Silva, Viviane Torres Rademaker, Alexandre Lionti, Krystelle Giro, Ronaldo Lima, Geisa Fiorini, Sandro Archanjo, Marcelo Carvalho, Breno W. Neumann, Rodrigo Souza, Anaximandro Souza, João Pedro de Valnisio, Gabriela Paz, Carmen Nilda Cerqueira, Renato Steiner, Mathias |
| author_facet | da Silva, Viviane Torres Rademaker, Alexandre Lionti, Krystelle Giro, Ronaldo Lima, Geisa Fiorini, Sandro Archanjo, Marcelo Carvalho, Breno W. Neumann, Rodrigo Souza, Anaximandro Souza, João Pedro de Valnisio, Gabriela Paz, Carmen Nilda Cerqueira, Renato Steiner, Mathias |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_03484 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature da Silva, Viviane Torres Rademaker, Alexandre Lionti, Krystelle Giro, Ronaldo Lima, Geisa Fiorini, Sandro Archanjo, Marcelo Carvalho, Breno W. Neumann, Rodrigo Souza, Anaximandro Souza, João Pedro de Valnisio, Gabriela Paz, Carmen Nilda Cerqueira, Renato Steiner, Mathias Materials Science Information Retrieval 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. |
| title | Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature |
| topic | Materials Science Information Retrieval |
| url | https://arxiv.org/abs/2411.03484 |