LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915587226075136 |
|---|---|
| author | Lederbauer, Magdalena Betala, Siddharth Li, Xiyao Jain, Ayush Sehaba, Amine Channing, Georgia Germain, Grégoire Leonescu, Anamaria Flaifil, Faris Amayuelas, Alfonso Nozadze, Alexandre Schmid, Stefan P. Zaki, Mohd Ethirajan, Sudheesh Kumar Pan, Elton Franckel, Mathilde Duval, Alexandre Krishnan, N. M. Anoop Gleason, Samuel P. |
| author_facet | Lederbauer, Magdalena Betala, Siddharth Li, Xiyao Jain, Ayush Sehaba, Amine Channing, Georgia Germain, Grégoire Leonescu, Anamaria Flaifil, Faris Amayuelas, Alfonso Nozadze, Alexandre Schmid, Stefan P. Zaki, Mohd Ethirajan, Sudheesh Kumar Pan, Elton Franckel, Mathilde Duval, Alexandre Krishnan, N. M. Anoop Gleason, Samuel P. |
| contents | The development of synthesis procedures remains a fundamental challenge in materials discovery, with procedural knowledge scattered across decades of scientific literature in unstructured formats that are challenging for systematic analysis. In this paper, we propose a multi-modal toolbox that employs large language models (LLMs) and vision language models (VLMs) to automatically extract and organize synthesis procedures and performance data from materials science publications, covering text and figures. We curated 81k open-access papers, yielding LeMat-Synth (v 1.0): a dataset containing synthesis procedures spanning 35 synthesis methods and 16 material classes, structured according to an ontology specific to materials science. The extraction quality is rigorously evaluated on a subset of 2.5k synthesis procedures through a combination of expert annotations and a scalable LLM-as-a-judge framework. Beyond the dataset, we release a modular, open-source software library designed to support community-driven extension to new corpora and synthesis domains. Altogether, this work provides an extensible infrastructure to transform unstructured literature into machine-readable information. This lays the groundwork for predictive modeling of synthesis procedures as well as modeling synthesis--structure--property relationships. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26824 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature Lederbauer, Magdalena Betala, Siddharth Li, Xiyao Jain, Ayush Sehaba, Amine Channing, Georgia Germain, Grégoire Leonescu, Anamaria Flaifil, Faris Amayuelas, Alfonso Nozadze, Alexandre Schmid, Stefan P. Zaki, Mohd Ethirajan, Sudheesh Kumar Pan, Elton Franckel, Mathilde Duval, Alexandre Krishnan, N. M. Anoop Gleason, Samuel P. Digital Libraries Artificial Intelligence Information Retrieval The development of synthesis procedures remains a fundamental challenge in materials discovery, with procedural knowledge scattered across decades of scientific literature in unstructured formats that are challenging for systematic analysis. In this paper, we propose a multi-modal toolbox that employs large language models (LLMs) and vision language models (VLMs) to automatically extract and organize synthesis procedures and performance data from materials science publications, covering text and figures. We curated 81k open-access papers, yielding LeMat-Synth (v 1.0): a dataset containing synthesis procedures spanning 35 synthesis methods and 16 material classes, structured according to an ontology specific to materials science. The extraction quality is rigorously evaluated on a subset of 2.5k synthesis procedures through a combination of expert annotations and a scalable LLM-as-a-judge framework. Beyond the dataset, we release a modular, open-source software library designed to support community-driven extension to new corpora and synthesis domains. Altogether, this work provides an extensible infrastructure to transform unstructured literature into machine-readable information. This lays the groundwork for predictive modeling of synthesis procedures as well as modeling synthesis--structure--property relationships. |
| title | LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature |
| topic | Digital Libraries Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2510.26824 |