Assessment of fine-tuned large language models for real-world chemistry and material science applications
Chemical Science · 2025 · 16 (2) · 670-684
DOI: 10.1039/d4sc04401k ↗Kurz gefasst
Fachartikel in der Zeitschrift Chemical Science, 2025. Verfasst von Joren Van Herck und 49 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'In…. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0). Gefördert von: European Research Council, Seventh Framework Programme, Cambridge Trust.
Abstract (Originalsprache)
We studied the performance of fine-tuning open-source LLMs for a range of different chemical questions. We benchmark their performances against “traditional” machine learning models and find that, in most cases, the fine-tuning approach is superior.
Autor:innen und Institutionen
- Laboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.
- Instituto de Ciencia y TecnologÍa del Carbono (INCAR), CSIC Francisco Pintado Fe 26 33011 Oviedo Spain.
- Laboratory of Organic and Tecnolog'ıa Chemistry (IOMC), Friedrich Schiller University Jena Humboldtstrasse 10 07743 Jena Germany.
- Helmholtz Institute for Polymers in Energy Applications Jena (HIPOLE Jena) Lessingstrasse 12-14 07743 Jena Germany.
- Yusuf Hamied Department of Chemistry, University of Cambridge Cambridge CB2 1EW UK.
- Department of Energy Conversion and Storage, Technical University of Denmark DK-2800 Kgs. Lyngby Denmark.
ORCID-Profile: Joren Van Herck, María Victoria Gil, Kevin Maik Jablonka, Alex Abrudan, Andy S Anker, Mehrdad Asgari, Ben Blaiszik, Antonio Buffo, Leander Choudhury, Clemence Corminboeuf, Hilal Daglar, Amir Mohammad Elahi, Ian T Foster, Susana Garcia, Matthew Garvin, Guillaume Godin, Lydia L Good, Jianan Gu, Noémie Xiao Hu, Xin Jin, Tanja Junkers, Seda Keskin, Tuomas P J Knowles, Ruben Laplaza, Michele Lessona, Sauradeep Majumdar, Hossein Mashhadimoslem, Ruaraidh D McIntosh, Seyed Mohamad Moosavi, Beatriz Mouriño, Francesca Nerli, Covadonga Pevida, Neda Poudineh, Mahyar Rajabi-Kochi, Kadi L Saar, Fahimeh Hooriabad Saboor, K J Schmidt, Jiale Shi, Elena Simone, Dennis Svatunek, Marco Taddei, Igor Tetko, Domonkos Tolnai, Sahar Vahdatifar, Jonathan Whitmer, D C Florian Wieland, Regine Willumeit-Römer, Andreas Züttel, Berend Smit
Förderung
- European Research Council
- Seventh Framework Programme
- Cambridge Trust
- National Institutes of Health
- Agencia Estatal de Investigación
- Consejo Superior de Investigaciones Científicas
- Ministerio de Ciencia e Innovación
- European Regional Development Fund
Zitieren
APA
Van Herck, J., Gil, M. V., Jablonka, K. M., Abrudan, A., Anker, A. S., Asgari, M., Blaiszik, B., Buffo, A., Choudhury, L., Corminboeuf, C., Daglar, H., Elahi, A. M., Foster, I. T., Garcia, S., Garvin, M., Godin, G., Good, L. L., Gu, J., Xiao Hu, N., …, & Smit, B. (2025). Assessment of fine-tuned large language models for real-world chemistry and material science applications. Chemical Science, 16(2), 670-684. https://doi.org/10.1039/d4sc04401k
Vancouver
Van Herck J, Gil MV, Jablonka KM, Abrudan A, Anker AS, Asgari M, et al. Assessment of fine-tuned large language models for real-world chemistry and material science applications. Chemical Science. 2025;16(2):670-684. doi:10.1039/d4sc04401k
BibTeX
@article{VanHerck2025,
author = {Van Herck, Joren and Gil, María Victoria and Jablonka, Kevin Maik and Abrudan, Alex and Anker, Andy S and Asgari, Mehrdad and Blaiszik, Ben and Buffo, Antonio and Choudhury, Leander and Corminboeuf, Clemence and Daglar, Hilal and Elahi, Amir Mohammad and Foster, Ian T and Garcia, Susana and Garvin, Matthew and Godin, Guillaume and Good, Lydia L and Gu, Jianan and Xiao Hu, Noémie and Jin, Xin and Junkers, Tanja and Keskin, Seda and Knowles, Tuomas P J and Laplaza, Ruben and Lessona, Michele and Majumdar, Sauradeep and Mashhadimoslem, Hossein and McIntosh, Ruaraidh D and Moosavi, Seyed Mohamad and Mouriño, Beatriz and Nerli, Francesca and Pevida, Covadonga and Poudineh, Neda and Rajabi-Kochi, Mahyar and Saar, Kadi L and Hooriabad Saboor, Fahimeh and Sagharichiha, Morteza and Schmidt, K J and Shi, Jiale and Simone, Elena and Svatunek, Dennis and Taddei, Marco and Tetko, Igor and Tolnai, Domonkos and Vahdatifar, Sahar and Whitmer, Jonathan and Wieland, D C Florian and Willumeit-Römer, Regine and Züttel, Andreas and Smit, Berend},
title = {Assessment of fine-tuned large language models for real-world chemistry and material science applications},
journal = {Chemical Science},
year = {2025},
volume = {16},
number = {2},
pages = {670--684},
doi = {10.1039/d4sc04401k}
}
EUVIMED