Materials science in the era of large language models: a perspective
Open accessThe DOI matches its Crossref record; 66 of the 66 references it cites were found in a registry or an index.
Abstract
This perspective paper explores the potential of Large Language Models (LLMs) in materials science, highlighting their abilities to handle ambiguous tasks, automate processes, and extract knowledge at scale across various disciplines.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453 · cited 1×
“Example PEFT schemes include LORA, 67 adapters 68 and prompt/pre x-tuning methods.”
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · cited 1×
“This reward is fed into a reinforcement learning policy, like Proximal Policy Optimization (PPO) 35 to update the weights.”
Weininger, D. (1988) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci00057a005 · Cited by 7,436 · cited 1×
“69,70 Textual representations of molecules like SMILES 71 and SELFIES 72 have seen success in transformer networks for property prediction 73,74 and molecular generation.”
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 1×
“A more thorough description is available in the ESI in Section S1.”
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
A learning algorithm for Boltzmann machines
Ackley, D. H., Hinton, G. E., & Sejnowski, T. J. (1985) · Cognitive Science · doi:10.1207/s15516709cog0901_7 · Cited by 3,402
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
Gómez-Bombarelli, R., Wei, J. N., Duvenaud, D., Hernández-Lobato, J. M., Sánchez-Lengeling, B., Sheberla, D., Aguilera-Iparraguirre, J., Hirzel, T. D., Adams, R. P., & Aspuru-Guzik, A. (2018) · ACS Central Science · doi:10.1021/acscentsci.7b00572 · Cited by 3,106
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.05232 · Cited by 2,516 · cited 4×
“Chain-of-thought reasoning can also sometimes mitigate logical hallucinations, 138 though asking a model to correct itself requires knowing the output was wrong in the rst place, reducing the value-add of LLMs. Microso Research AI4Science noted some hallucinations of GPT-4 whilst handling…”
InfluentialRevisiting Unreasonable Effectiveness of Data in Deep Learning Era
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.97 · Cited by 2,484
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Li, X. L., & Liang, P. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.353 · Cited by 2,473
Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1516 · Cited by 2,428
Longformer: The Long-Document Transformer
Beltagy, I., Peters, M. E., & Cohan, A. (2020) · arXiv · doi:10.48550/arxiv.2004.05150 · Cited by 2,281
Shortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224
Li, J., Li, D., Xiong, C., & Hoi, S. (2022) · arXiv · doi:10.48550/arxiv.2201.12086 · Cited by 1,741
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Gu, A., & Dao, T. (2023) · arXiv · doi:10.48550/arxiv.2312.00752 · Cited by 1,579 · cited 1×
“The quadratic scaling is the major downside of transformers and researchers are looking to mitigate this with techniques like windowed attention 22 or moving to linear state-space models like Mamba, 23 though these approaches lose global context.”
Cellpose 2.0: how to train your own model
Pachitariu, M., & Stringer, C. (2022) · Nature Methods · doi:10.1038/s41592-022-01663-4 · Cited by 1,381
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304
Emergent Abilities of Large Language Models
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.07682 · Cited by 1,264
Toolformer: Language Models Can Teach Themselves to Use Tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv · doi:10.48550/arxiv.2302.04761 · Cited by 1,150
Unsupervised word embeddings capture latent knowledge from materials science literature
Tshitoyan, V., Dagdelen, J., Weston, L., Dunn, A., Rong, Z., Kononova, O., Persson, K. A., Ceder, G., & Jain, A. (2019) · Nature · doi:10.1038/s41586-019-1335-8 · Cited by 1,123 · cited 1×
“126,127 These NLP approaches can be combined with web-scraping to create extractor tools like ‘ ChemDataExtractor ’ 128,129 and ‘ MatSciE ’ , 130 which aim to automatically create datasets from text entities and tabular data in papers matching a given search query.”
Reflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087 · cited 1×
“100,101 Another more involved approach used by Toolformer 99 was to use ICL to make LLMs annotate an existing language dataset with API calls for a variety of tools where it deemed them useful.”
Deep reinforcement learning from human preferences
Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017) · arXiv · doi:10.48550/arxiv.1706.03741 · Cited by 1,058 · cited 1×
“2 Self-supervised learning requires little or no human input – massive text datasets can be collected through automated web-scraping 27 – and generates strong learned representations.”
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 · cited 2×
“‘ Coscientist ’ 18 used LLMs as a coordinator to design, plan and execute chemical research.”
An autonomous laboratory for the accelerated synthesis of inorganic materials
Szymanski, N. J., Rendy, B., Fei, Y., Kumar, R. E., He, T., Milsted, D., McDermott, M. J., Gallant, M., Cubuk, E. D., Merchant, A., et al. (2023) · Nature · doi:10.1038/s41586-023-06734-w · Cited by 1,041 · cited 1×
“18,19 They are typically more exible and adaptable than traditional computer programs, making them more e ff ective when run continuously.”
Gemini: A Family of Highly Capable Multimodal Models
Gemini Team, Anil, R., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.11805 · Cited by 990
Retrieval-Augmented Generation for Large Language Models: A Survey
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876 · cited 1×
“95 RAG has several bene ts to LLM work ows: 96 rstly, hallucinations are reduced as models only need to process existing information in a prompt rather than generate (or fabricate) it.”
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. (2023) · arXiv · doi:10.48550/arxiv.2302.11382 · Cited by 838
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
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2022) · arXiv · doi:10.48550/arxiv.2202.12837 · Cited by 752
Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023) · arXiv · doi:10.48550/arxiv.2304.08485 · Cited by 682
Explainability for Large Language Models: A Survey
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681
ReAct: Synergizing Reasoning and Acting in Language Models
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.03629 · Cited by 608
Swain, M. C., & Cole, J. M. (2016) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6b00207 · Cited by 598
PaLM-E: An Embodied Multimodal Language Model
Driess, D., Xia, F., Sajjadi, M. S. M., Lynch, C., Chowdhery, A., Ichter, B., Wahid, A., Tompson, J., Vuong, Q., Yu, T., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.03378 · Cited by 591
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.04615 · Cited by 569
Mathematical discoveries from program search with large language models
Romera-Paredes, B., Barekatain, M., Novikov, A., Balog, M., Kumar, M. P., Dupont, E., Ruiz, F. J. R., Ellenberg, J. S., Wang, P., Fawzi, O., et al. (2024) · Nature · doi:10.1038/s41586-023-06924-6 · Cited by 544 · cited 1×
“15 Whilst they perform best in work ows with a strong, LLM-independent feedback signal 16 they are capable of automating processes in ambiguous scenarios through trial-and-error.”
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.02643 · Cited by 527
A generative model for inorganic materials design
Zeni, C., Pinsler, R., Zügner, D., Fowler, A., Horton, M., Fu, X., Wang, Z., Shysheya, A., Crabbé, J., Ueda, S., et al. (2025) · Nature · doi:10.1038/s41586-025-08628-5 · Cited by 518
ViperGPT: Visual Inference via Python Execution for Reasoning
Surís, D., Menon, S., & Vondrick, C. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01092 · Cited by 273
WebGPT: Browser-assisted question-answering with human feedback
Nakano, R., Hilton, J., Balaji, S., Wu, J., Ouyang, L., Kim, C., Hesse, C., Jain, S., Kosaraju, V., Saunders, W., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.09332 · Cited by 272
Large Language Models Can Self-Improve
Huang, J., Gu, S. S., Hou, L., Wu, Y., Wang, X., Yu, H., & Han, J. (2022) · arXiv · doi:10.48550/arxiv.2210.11610 · Cited by 230 · cited 1×
“59 Self-re ection improves performance, potentially for the same reasons as ICL and CoT, but also because correcting a wrong output may be a simpler task than generating the correct output de novo .”
Large Language Models Can Self-Improve
Huang, J., Gu, S., Hou, L., Wu, Y., Wang, X., Yu, H., & Han, J. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.67 · Cited by 230
Jablonka, 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
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., & Duan, N. (2023) · arXiv · doi:10.48550/arxiv.2303.04671 · Cited by 197
Position Information in Transformers: An Overview
Dufter, P., Schmitt, M., & Schütze, H. (2022) · Computational Linguistics · doi:10.1162/coli_a_00445 · Cited by 175
Penedo, G., Malartic, Q., Hesslow, D., Cojocaru, R., Cappelli, A., Alobeidli, H., Pannier, B., Almazrouei, E., & Launay, J. (2023) · arXiv · doi:10.48550/arxiv.2306.01116 · Cited by 164 · cited 1×
“8,9 Despite their simple training objective of reproducing human-like text, 10 the combination of broad training data and deep networks has resulted in impressive emergent capabilities and applicability to di ff erent domains and problems.”
Large Language Models as Optimizers
Yang, C., Wang, X., Lu, Y., Liu, H., Le, Q. V., Zhou, D., & Chen, X. (2023) · arXiv · doi:10.48550/arxiv.2309.03409 · Cited by 151 · cited 4×
“…than a science, but some work has been done on creating and testing various principles 46,47 or using an LLM to optimise prompts for another LLM. 48 It has been found that it is generally better to be precise, structured (using paragraphs, whitespace and question/answer blocks) and explain to…”
InfluentialNeural scaling of deep chemical models
Frey, N. C., Soklaski, R., Axelrod, S., Samsi, S., Gómez-Bombarelli, R., Coley, C. W., & Gadepally, V. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00740-3 · Cited by 125
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
Larger language models do in-context learning differently
Wei, J., Wei, J., Tay, Y., Tran, D., Webson, A., Lu, Y., Chen, X., Liu, H., Huang, D., Zhou, D., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.03846 · Cited by 109
Buehler, M. J. (2024) · ACS Engineering Au · doi:10.1021/acsengineeringau.3c00058 · Cited by 82
Emergent autonomous scientific research capabilities of large language models
Boiko, D. A., MacKnight, R., & Gomes, G. (2023) · arXiv · doi:10.48550/arxiv.2304.05332 · Cited by 72
OLMo: Accelerating the Science of Language Models
Groeneveld, D., Beltagy, I., Walsh, E., Bhagia, A., Kinney, R., Tafjord, O., Jha, A., Ivison, H., Magnusson, I., Wang, Y., et al. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.841 · Cited by 70
MemGPT: Towards LLMs as Operating Systems
Packer, C., Wooders, S., Lin, K., Fang, V., Patil, S. G., Stoica, I., & Gonzalez, J. E. (2023) · arXiv · doi:10.48550/arxiv.2310.08560 · Cited by 64 · cited 1×
“As well as contributing towards hallucinations, data duplication (alongside autoregression and the pre-training objective) can also contribute to an LLM's tendency to output towards a generic or modal answer.”
Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions
Yang, H., Yue, S., & He, Y. (2023) · arXiv · doi:10.48550/arxiv.2306.02224 · Cited by 44 · cited 1×
“15 Whilst they perform best in work ows with a strong, LLM-independent feedback signal 16 they are capable of automating processes in ambiguous scenarios through trial-and-error.”
DERA: Enhancing large language model completions with dialog-enabled resolving agents
Nair, V., Schumacher, E., Tso, G., & Kannan, A. (2024) · Proceedings of the 6th Clinical Natural Language Processing Workshop · doi:10.18653/v1/2024.clinicalnlp-1.12 · Cited by 38
Large language models as tool makers
Cai, T., Wang, X., Ma, T., Chen, X., & Zhou, D. (2023) · arXiv · doi:10.48550/arxiv.2305.17126 · Cited by 28 · cited 1×
“These xes for hallucinations exist mostly at the dataset or training level, which is di ffi cult for all but the largest research groups to manage.”
Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering
Ridnik, T., Kredo, D., & Friedman, I. (2024) · arXiv · doi:10.48550/arxiv.2401.08500 · Cited by 23
World Model on Million-Length Video And Language With Blockwise RingAttention
Liu, H., Yan, W., Zaharia, M., & Abbeel, P. (2024) · arXiv · doi:10.48550/arxiv.2402.08268 · Cited by 14 · cited 1×
“Multi-modality has become an increasingly important focus of LLMs, 50,92 with recent examples like GPT-4o being ‘ natively multi-modal ’ , 93 meaning they are trained to input and output tokens of various modalities (rather than, say, generating an image by producing text to describe the image and…”
OLMo: Accelerating the Science of Language Models
Groeneveld, D., Beltagy, I., Walsh, P., Bhagia, A., Kinney, R., Tafjord, O., Jha, A. H., Ivison, H., Magnusson, I., Wang, Y., et al. (2024) · arXiv · doi:10.48550/arxiv.2402.00838 · Cited by 10 · cited 1×
“8,9 Despite their simple training objective of reproducing human-like text, 10 the combination of broad training data and deep networks has resulted in impressive emergent capabilities and applicability to di ff erent domains and problems.”
Mitigating the Alignment Tax of RLHF
Lin, Y., Lin, H., Xiong, W., Diao, S., Liu, J., Zhang, J., Pan, R., Wang, H., Hu, W., Zhang, H., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.06256 · Cited by 10
Cited by
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
Lin, J., Zhao, D., Lu, S., Li, R., Xu, X., Wang, Z., Li, W., Ji, Y., Zhang, C., Shi, L., et al. (2025) · ACS Nano · doi:10.1021/acsnano.5c04880 · Cited by 36
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-guided large language model for material science
Wang, G., Hu, J., Zhou, J., Liu, S., Li, Q., & Sun, Z. (2025) · Review of Materials Research · doi:10.1016/j.revmat.2025.100007 · Cited by 16
Metadata
- Authors
- Lei, G., Docherty, R., & Cooper, S. J.
- Venue
- Digital Discovery
- Publisher
- Royal Society of Chemistry (RSC)
- Published
- 2024
- Volume
- 3
- Issue
- 7
- Pages
- 1257-1272
- ISSN
- 2635-098X (ISSN-L)
- OpenAlex
- W4399377978
- Cited by
- 99
- References
- 66
- FWCI
- 9.40
- Type
- journal article
- Language
- en
- Open access
- diamond
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.