{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:17:20Z","timestamp":1784269040013,"version":"3.55.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0711900"],"award-info":[{"award-number":["2022YFF0711900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0712200"],"award-info":[{"award-number":["2022YFF0712200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["T2322027"],"award-info":[{"award-number":["T2322027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s13042-024-02473-0","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T15:14:30Z","timestamp":1736954070000},"page":"3681-3691","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["CataLM: empowering catalyst design through large language models"],"prefix":"10.1007","volume":"16","author":[{"given":"Ludi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueqing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanchun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjuan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"issue":"6438","key":"2473_CR1","doi-asserted-by":"publisher","first-page":"3506","DOI":"10.1126\/science.aav3506","volume":"364","author":"P De Luna","year":"2019","unstructured":"De Luna P, Hahn C, Higgins D, Jaffer SA, Jaramillo TF, Sargent EH (2019) What would it take for renewably powered electrosynthesis to displace petrochemical processes? Science 364(6438):3506","journal-title":"Science"},{"issue":"6321","key":"2473_CR2","doi-asserted-by":"publisher","first-page":"4998","DOI":"10.1126\/science.aad4998","volume":"355","author":"ZW Seh","year":"2017","unstructured":"Seh ZW, Kibsgaard J, Dickens CF, Chorkendorff I, N\u00f8rskov JK, Jaramillo TF (2017) Combining theory and experiment in electrocatalysis: Insights into materials design. Science 355(6321):4998","journal-title":"Science"},{"issue":"1","key":"2473_CR3","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1038\/nchem.121","volume":"1","author":"JK N\u00f8rskov","year":"2009","unstructured":"N\u00f8rskov JK, Bligaard T, Rossmeisl J, Christensen CH (2009) Towards the computational design of solid catalysts. Nat Chem 1(1):37\u201346","journal-title":"Nat Chem"},{"issue":"6061","key":"2473_CR4","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1126\/science.1212858","volume":"334","author":"J Suntivich","year":"2011","unstructured":"Suntivich J, May KJ, Gasteiger HA, Goodenough JB, Shao-Horn Y (2011) A perovskite oxide optimized for oxygen evolution catalysis from molecular orbital principles. Science 334(6061):1383\u20131385","journal-title":"Science"},{"issue":"1","key":"2473_CR5","doi-asserted-by":"publisher","first-page":"1901614","DOI":"10.1002\/advs.201901614","volume":"7","author":"J Liu","year":"2020","unstructured":"Liu J, Liu H, Chen H, Du X, Zhang B, Hong Z, Sun S, Wang W (2020) Progress and challenges toward the rational design of oxygen electrocatalysts based on a descriptor approach. Adv Sci 7(1):1901614","journal-title":"Adv Sci"},{"key":"2473_CR6","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"2473_CR7","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"2473_CR8","unstructured":"Clark K, Luong M-T, Le QV (2020) Manning, CD Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555"},{"key":"2473_CR9","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I et al (2018) Improving language understanding by generative pre-training"},{"issue":"8","key":"2473_CR10","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I et al (2019) Language models are unsupervised multitask learners. OpenAI Blog 1(8):9","journal-title":"OpenAI Blog"},{"key":"2473_CR11","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. In: Advances in neural information processing systems vol. 33, p. 1877\u20131901"},{"key":"2473_CR12","unstructured":"OpenAI R (2023) Gpt-4 technical report. ArXiv:2303.08774"},{"issue":"140","key":"2473_CR13","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(140):1\u201367","journal-title":"J Mach Learn Res"},{"key":"2473_CR14","unstructured":"Gao L, Biderman S, Black S, Golding L, Hoppe T, Foster C, Phang J, He H, Thite A, Nabeshima N et al (2020) The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027"},{"issue":"6","key":"2473_CR15","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1093\/bib\/bbac409","volume":"23","author":"R Luo","year":"2022","unstructured":"Luo R, Sun L, Xia Y, Qin T, Zhang S, Poon H, Liu T-Y (2022) Biogpt: generative pre-trained transformer for biomedical text generation and mining. Brief Bioinformatics 23(6):409","journal-title":"Brief Bioinformatics"},{"key":"2473_CR16","doi-asserted-by":"crossref","unstructured":"Zhang H, Chen J, Jiang F, Yu F, Chen Z, Li J, Chen G, Wu X, Zhang Z, Xiao Q et al (2023) Huatuogpt, towards taming language model to be a doctor. arXiv preprint arXiv:2305.15075","DOI":"10.18653\/v1\/2023.findings-emnlp.725"},{"key":"2473_CR17","unstructured":"Xiong H, Wang S, Zhu Y, Zhao Z, Liu Y, Huang L, Wang Q, Shen D (2023) Doctorglm: Fine-tuning your chinese doctor is not a herculean task. arXiv preprint arXiv:2304.01097"},{"issue":"5","key":"2473_CR18","doi-asserted-by":"publisher","DOI":"10.1088\/0256-307X\/40\/5\/057401","volume":"40","author":"F Xie","year":"2023","unstructured":"Xie F, Lu T, Yu Z, Wang Y, Wang Z, Meng S, Liu M (2023) Lu-h-n phase diagram from first-principles calculations. Chin Phys Lett 40(5):057401","journal-title":"Chin Phys Lett"},{"key":"2473_CR19","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.1007\/s11837-013-0755-4","volume":"65","author":"JE Saal","year":"2013","unstructured":"Saal JE, Kirklin S, Aykol M, Meredig B, Wolverton C (2013) Materials design and discovery with high-throughput density functional theory: the open quantum materials database (oqmd). Jom 65:1501\u20131509","journal-title":"Jom"},{"issue":"1","key":"2473_CR20","doi-asserted-by":"publisher","DOI":"10.1063\/1.4812323","volume":"1","author":"A Jain","year":"2013","unstructured":"Jain A, Ong SP, Hautier G, Chen W, Richards WD, Dacek S, Cholia S, Gunter D, Skinner D, Ceder G et al (2013) Commentary: The materials project: A materials genome approach to accelerating materials innovation. APL Mater 1(1):011002","journal-title":"APL Mater"},{"issue":"1","key":"2473_CR21","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/s40843-022-2134-3","volume":"66","author":"Y Liang","year":"2023","unstructured":"Liang Y, Chen M, Wang Y, Jia H, Lu T, Xie F, Cai G, Wang Z, Meng S, Liu M (2023) A universal model for accurately predicting the formation energy of inorganic compounds. Sci China Mater 66(1):343\u2013351","journal-title":"Sci China Mater"},{"key":"2473_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2022.111699","volume":"214","author":"Z Liu","year":"2022","unstructured":"Liu Z, Guo J, Chen Z, Wang Z, Sun Z, Li X, Wang Y (2022) Swarm intelligence for new materials. Comput Mater Sci 214:111699","journal-title":"Comput Mater Sci"},{"issue":"1","key":"2473_CR23","first-page":"15326","volume":"12","author":"J Guo","year":"2022","unstructured":"Guo J, Chen Z, Liu Z, Li X, Xie Z, Wang Z, Wang Y (2022) Neural network training method for materials science based on multi-source databases. Sci Reports 12(1):15326","journal-title":"Sci Reports"},{"issue":"1","key":"2473_CR24","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1038\/s41524-022-00784-w","volume":"8","author":"T Gupta","year":"2022","unstructured":"Gupta T, Zaki M, Krishnan NA, Mausam (2022) Matscibert: A materials domain language model for text mining and information extraction. NPJ Comput Mater 8(1):102","journal-title":"NPJ Comput Mater"},{"issue":"11","key":"2473_CR25","doi-asserted-by":"publisher","DOI":"10.1088\/1674-1056\/ad04cb","volume":"32","author":"Z-Y Chen","year":"2023","unstructured":"Chen Z-Y, Xie F-K, Wan M, Yuan Y, Liu M, Wang Z-G, Meng S, Wang Y-G (2023) Matchat: a large language model and application service platform for materials science. Chin Phys B 32(11):118104. https:\/\/doi.org\/10.1088\/1674-1056\/ad04cb","journal-title":"Chin Phys B"},{"key":"2473_CR26","doi-asserted-by":"crossref","unstructured":"Xie T, Wan Y, Huang W, Zhou Y, Liu Y, Linghu Q, Wang S, nCG, Zhang W, Hoex B (2023) Large language models as master key: unlocking the secrets of materials science with GPT arXiv:2304.02213","DOI":"10.2139\/ssrn.4534137"},{"issue":"32","key":"2473_CR27","doi-asserted-by":"publisher","first-page":"18048","DOI":"10.1021\/jacs.3c05819","volume":"145","author":"Z Zheng","year":"2023","unstructured":"Zheng Z, Zhang O, Borgs C, Chayes JT, Yaghi OM (2023) Chatgpt chemistry assistant for text mining and the prediction of mof synthesis. J Am Chem Soc 145(32):18048\u201318062. https:\/\/doi.org\/10.1021\/jacs.3c05819","journal-title":"J Am Chem Soc"},{"key":"2473_CR28","unstructured":"Cao H, Liu Z, Lu X, Yao Y, Li Y (2023) InstructMol: multi-modal integration for building a versatile and reliable molecular assistant in drug discovery. arXiv preprint arXiv:2311.16208"},{"key":"2473_CR29","unstructured":"Barroso-Luque L, Shuaibi M, Fu X, Wood BM, Dzamba M, Gao M, Rizvi A, Zitnick CL, Ulissi ZW (2024) Open materials 2024 (omat24) inorganic materials dataset and models. arXiv preprint arXiv:2410.12771"},{"key":"2473_CR30","doi-asserted-by":"crossref","unstructured":"Leong SX, Pablo-Garc\u00eda S, Zhang Z, Aspuru-Guzik A (2024) Automated electrosynthesis reaction mining with multimodal large language models (mllms). Chemical Science. arXiv preprint arXiv:2311.16208","DOI":"10.26434\/chemrxiv-2024-7fwxv"},{"issue":"2","key":"2473_CR31","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-024-00795-w","volume":"6","author":"M Kulmanov","year":"2024","unstructured":"Kulmanov M, Guzm\u00e1n-Vega FJ, Duek Roggli P, Lane L, Arold ST, Hoehndorf R (2024) Protein function prediction as approximate semantic entailment. Nat Mach Intell 6(2):220\u2013228","journal-title":"Nat Mach Intell"},{"issue":"1","key":"2473_CR32","first-page":"28","volume":"2","author":"J Qian","year":"2024","unstructured":"Qian J, Jin Z, Zhang Q, Cai G, Liu B (2024) A liver cancer question-answering system based on next-generation intelligence and the large model med-palm 2. Int J Comput Sci Inf Technol 2(1):28\u201335","journal-title":"Int J Comput Sci Inf Technol"},{"key":"2473_CR33","unstructured":"Wu C, Zhang X, Zhang Y, Wang Y, Xie W (2023) Pmc-llama: Further finetuning llama on medical papers. arXiv preprint arXiv:2304.14454"},{"key":"2473_CR34","doi-asserted-by":"crossref","unstructured":"Chen B, Cheng X, Li P, Geng Y-a, Gong J, Li S, Bei Z, Tan X, Wang B, Zeng X et al (2024) xtrimopglm: unified 100b-scale pre-trained transformer for deciphering the language of protein. arXiv preprint arXiv:2401.06199","DOI":"10.1101\/2023.07.05.547496"},{"key":"2473_CR35","unstructured":"Liu R, McKie J (2018) PyMuPDF. May. http:\/\/pymupdf.readthedocs.io\/en\/latest\/"},{"key":"2473_CR36","doi-asserted-by":"crossref","unstructured":"Beltagy I, Lo K, Cohan A (2019) Scibert: A pretrained language model for scientific text. arXiv preprint arXiv:1903.10676","DOI":"10.18653\/v1\/D19-1371"},{"key":"2473_CR37","doi-asserted-by":"crossref","unstructured":"Wang Y, Kordi Y, Mishra S, Liu A, Smith NA, Khashabi D, Hajishirzi H (2022) Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"2473_CR38","unstructured":"Qin Y, Liang S, Ye Y, Zhu K, Yan L, Lu Y, Lin Y, Cong X, Tang X, Qian B et al (2023) Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789"},{"issue":"1","key":"2473_CR39","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1038\/s41597-023-02089-z","volume":"10","author":"L Wang","year":"2023","unstructured":"Wang L, Gao Y, Chen X, Cui W, Zhou Y, Luo X, Xu S, Du Y, Wang B (2023) A corpus of co2 electrocatalytic reduction process extracted from the scientific literature. Sci Data 10(1):175","journal-title":"Sci Data"},{"key":"2473_CR40","doi-asserted-by":"crossref","unstructured":"Du Y, Wang L, Huang M, Song D, Cui W, Zhou Y (2023) Autodive: An integrated onsite scientific literature annotation tool. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 76\u201385","DOI":"10.18653\/v1\/2023.acl-demo.7"},{"key":"2473_CR41","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2021) LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685"},{"key":"2473_CR42","doi-asserted-by":"crossref","unstructured":"Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P, Rault T, Louf R, Funtowicz M, Davison J, Shleifer S, Platen P, Ma C, Jernite Y, Plu J, Xu C, Scao TL, Gugger S, Drame M, Lhoest Q, Rush AM (2020) Transformers: State-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online . https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"2473_CR43","doi-asserted-by":"crossref","unstructured":"Wang X, Hu V, Song X, Garg S, Xiao J, Han J (2021) Chemner: Fine-grained chemistry named entity recognition with ontology-guided distant supervision. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/2021.emnlp-main.424"},{"key":"2473_CR44","doi-asserted-by":"publisher","first-page":"8525","DOI":"10.1021\/acscatal.3c00759","volume":"13","author":"Y Gao","year":"2023","unstructured":"Gao Y, Wang L, Chen X, Du Y, Wang B (2023) Revisiting electrocatalyst design by a knowledge graph of cu-based catalysts for co 2 reduction. ACS Catal 13:8525\u20138534. https:\/\/doi.org\/10.1021\/acscatal.3c00759","journal-title":"ACS Catal"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02473-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02473-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02473-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:32:09Z","timestamp":1749270729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02473-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,15]]},"references-count":44,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2473"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02473-0","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,15]]},"assertion":[{"value":"26 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}