Large Language Models for Inorganic Synthesis Predictions
Open accessPublished version of a preprint
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
We evaluate the effectiveness of pretrained and fine-tuned large language models (LLMs) for predicting the synthesizability of inorganic compounds and the selection of precursors needed to perform inorganic synthesis. The predictions of fine-tuned LLMs are comparable to─and sometimes better than─recent bespoke machine learning models for these tasks but require only minimal user expertise, cost, and time to develop. Therefore, this strategy can serve both as an effective and strong baseline for future machine learning studies of various chemical applications and as a practical tool for experimental chemists.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Autonomous chemical research with large language models
Boiko, D. A., MacKnight, R., Kline, B., & Gomes, G. (2023) · Nature · doi:10.1038/s41586-023-06792-0 · Cited by 1,050
Augmenting large language models with chemistry tools
M. Bran, A., Cox, S., Schilter, O., Baldassari, C., White, A. D., & Schwaller, P. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00832-8 · Cited by 794
Learning from positive and unlabeled data: a survey
Bekker, J., & Davis, J. (2020) · Machine Learning · doi:10.1007/s10994-020-05877-5 · Cited by 651
Leveraging large language models for predictive chemistry
Jablonka, K. M., Schwaller, P., Ortega-Guerrero, A., & Smit, B. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-023-00788-1 · Cited by 378
Polak, M. P., & Morgan, D. (2024) · Nature Communications · doi:10.1038/s41467-024-45914-8 · Cited by 365
Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis
Jia, X., Lynch, A., Huang, Y., Danielson, M., Lang’at, I., Milder, A., Ruby, A. E., Wang, H., Friedler, S. A., Norquist, A. J., et al. (2019) · Nature · doi:10.1038/s41586-019-1540-5 · Cited by 222
Self-citationJablonka, K. M., Ai, Q., Al-Feghali, A., Badhwar, S., Bocarsly, J. D., Bran, A. M., Bringuier, S., Brinson, L. C., Choudhary, K., Circi, D., et al. (2023) · Digital Discovery · doi:10.1039/d3dd00113j · Cited by 218
Virtual screening of inorganic materials synthesis parameters with deep learning
Kim, E., Huang, K., Jegelka, S., & Olivetti, E. (2017) · npj Computational Materials · doi:10.1038/s41524-017-0055-6 · Cited by 190
ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs
Zheng, Z., Zhang, O., Nguyen, H. L., Rampal, N., Alawadhi, A. H., Rong, Z., Head-Gordon, T., Borgs, C., Chayes, J. T., & Yaghi, O. M. (2023) · ACS Central Science · doi:10.1021/acscentsci.3c01087 · Cited by 172
ChemCrow: Augmenting large-language models with chemistry tools
Bran, A. M., Cox, S., Schilter, O., Baldassari, C., White, A. D., & Schwaller, P. (2023) · arXiv · doi:10.48550/arxiv.2304.05376 · Cited by 122
Research works printed but not linked: 49
- 10.1038/s44160-022-00096-3 · DOI · Paper page
- 10.1007/BF01507527 · DOI · Paper page
- 10.1126/sciadv.aav0693 · DOI · Paper page
- 10.1038/s41467-021-26006-3 · DOI
- 10.1017/9781139025348 · doi:10.1017/9781139025348
- West A. R., 2022, Solid State Chemistry and Its Applications
- 10.1021/jacs.0c07384 · DOI
- 10.1038/s41524-022-00757-z · DOI
- 10.1039/D2DD00098A · DOI
- 10.1021/acsomega.2c04856 · DOI
- 10.1038/s41524-023-01114-4 · DOI
- 10.1021/acs.jcim.9b00995 · DOI · Paper page
- 10.1126/sciadv.adg8180 · DOI
- 10.1039/D3SC03538G · DOI
- 10.1038/s41570-022-00382-w · DOI
- 10.1039/D3DD00213F · DOI
- 10.1021/jacs.2c13467 · DOI · Paper page
- 10.1021/acs.jcim.3c01977 · DOI
- 10.1021/jacs.3c05819 · DOI · Paper page
- 10.1039/D3DD00202K · DOI
- 10.1088/2632-2153/ad2f52 · DOI
- 10.1039/D2DD00087C · DOI · Paper page
- 10.1021/acs.jchemed.4c00058 · DOI
- 10.1021/jacs.3c12086 · DOI · Paper page
- 10.1002/anie.202311983 · DOI · Paper page
- 10.1039/D3DD00188A · DOI
- 10.1021/acs.jcim.3c01702 · DOI · Paper page
- 10.1080/27660400.2023.2260300 · DOI
- Guo T., 2023, Advances in Neural Information Processing Systems, 36, 59662
- 10.48550/arXiv.2311.07361 · arXiv · doi:10.48550/arxiv.2311.07361 · Paper page
- 10.48550/arXiv.2404.01475 · DOI
- 10.1002/adma.202306733 · DOI
- 10.48550/arXiv.2402.06852 · DOI
- 10.1039/D3SC04610A · DOI
- 10.1021/acs.estlett.3c00599 · DOI
- 10.48550/arXiv.2403.05075 · DOI
- 10.1145/1401890.1401920 · DOI · Paper page
- 10.1137/1.9781611972795.23 · DOI · Paper page
- 10.1016/j.matt.2024.05.002 · DOI
- 10.1063/1.4812323 · DOI · Paper page
- 10.1038/npjcompumats.2015.10 · DOI · Paper page
- 10.1609/aaai.v31i1.10937 · DOI · Paper page
- 10.48550/arXiv.2304.05341 · DOI
- 10.1016/j.patcog.2012.03.004 · DOI · Paper page
- 10.1038/s41597-019-0224-1 · DOI · Paper page
- 10.1145/3632366.3632396 · DOI
- 10.48550/arXiv.2402.09391 · DOI
- 10.1021/jacs.1c12005 · DOI · Paper page
- 10.1021/jacs.3c04783 · DOI
Cited by
A Multiagent-Driven Robotic AI Chemist Enabling Autonomous Chemical Research On Demand
Song, T., Luo, M., Zhang, X., Chen, L., Huang, Y., Cao, J., Zhu, Q., Liu, D., Zhang, B., Zou, G., et al. (2025) · Journal of the American Chemical Society · doi:10.1021/jacs.4c17738 · Cited by 171
Large language models for reticular chemistry
Zheng, Z., Rampal, N., Inizan, T. J., Borgs, C., Chayes, J. T., & Yaghi, O. M. (2025) · Nature Reviews Materials · doi:10.1038/s41578-025-00772-8 · Cited by 134
“As an alternative approach, LLMs themselves can be fine-tuned to predict the formation of inorganic compounds based on a given set of precursors 62 .”
Developing ChemDFM as a large language foundation model for chemistry
Zhao, Z., Ma, D., Chen, L., Sun, L., Li, Z., Xia, Y., Chen, B., Xu, H., Zhu, Z., Zhu, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2401.14818 · Cited by 48
Language models for materials discovery and sustainability: Progress, challenges, and opportunities
Pei, Z., Yin, J., & Zhang, J. (2025) · Progress in Materials Science · doi:10.1016/j.pmatsci.2025.101495 · Cited by 30
Knowledge-driven autonomous materials research via collaborative multi-agent and robotic system
Shi, T., Li, Y., Wang, Z., Xu, W., Jiang, G., Dai, D., Zhou, J., Huang, H., He, R., Ramakrishna, S., et al. (2026) · Matter · doi:10.1016/j.matt.2025.102577 · Cited by 16
VASPilot: MCP-facilitated multi-agent intelligence for autonomous VASP simulations
Liu 刘, J. 家., Zhu 朱, T. 天., Ye 叶, C. 财., Fang 方, Z. 忠., Weng 翁, H. 红., & Wu 吴, Q. 泉. (2025) · Chinese Physics B · doi:10.1088/1674-1056/ae0681 · Cited by 7
Metadata
- Authors
- Kim, S., Jung, Y., & Schrier, J.
- Venue
- Journal of the American Chemical Society
- Publisher
- American Chemical Society (ACS)
- Published
- 2024-07-11
- Volume
- 146
- Issue
- 29
- Pages
- 19654-19659
- ISSN
- 0002-7863 (ISSN-L)
- 1520-5126
- OpenAlex
- W4400524753
- Cited by
- 73
- References
- 14
- FWCI
- 6.93
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- Funders
- Fordham University
- U.S. Department of Energy (KC0302031)
- National Research Foundation of Korea (2021R1A5A1030054, RS-2023-00283902)
- Ministry of Science, ICT and Future Planning (RS-2021-II211343)
- Seoul National University
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.