The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Extracting accurate materials data from research papers with conversational language models and prompt engineering
Open accessAbstract
There has been a growing effort to replace manual extraction of data from research papers with automated data extraction based on natural language processing, language models, and recently, large language models (LLMs). Although these methods enable efficient extraction of data from large sets of research papers, they require a significant amount of up-front effort, expertise, and coding. In this work, we propose the method that can fully automate very accurate data extraction with minimal initial effort and background, using an advanced conversational LLM. consists of a set of engineered prompts applied to a conversational LLM that both identify sentences with data, extract that data, and assure the data’s correctness through a series of follow-up questions. These follow-up questions largely overcome known issues with LLMs providing factually inaccurate responses. can be applied with any conversational LLMs and yields very high quality data extraction. In tests on materials data, we find precision and recall both close to 90% from the best conversational LLMs, like GPT-4. We demonstrate that the exceptional performance is enabled by the information retention in a conversational model combined with purposeful redundancy and introducing uncertainty through follow-up prompts. These results suggest that approaches similar to , due to their simplicity, transferability, and accuracy are likely to become powerful tools for data extraction in the near future. Finally, databases for critical cooling rates of metallic glasses and yield strengths of high entropy alloys are developed using .
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
Figures

![Fig. 2 A flowchart describing our ChatExtract method of extracting structured data using a conversational large language model. Blue boxes represent prompts given to the model, gray boxes are instructions to the user, “Yes”, “No”, and “None” boxes are model’s responses. The bold text in “[]” are to be replaced with appropriate values of the named item, which includes one of sentence (the target sentence being analyzed); text (the expanded text consisting of Title, Preceding sentence, and target sentence); name of the property; extracted material, value, or unit.](https://figures.cochat.ai/paper-figures/170d56d8b8904c2da01e43ed3a0054f0/extracting-accurate-materials-data-from-research-papers-with-conversational-figure-2.jpg)
![Fig. 3 A flowchart describing our ChatExtract method of extracting structured data from tables figures using a conversational large language model. Panel (a) contains a flowchart for extracting data from tables while panel (b) contains a flowchart for extracting data from figures. Blue boxes represent prompts given to the model, gray boxes are instructions to the user, “Yes”, “No” boxes are model’s responses. The bold text in “[]” are to be replaced with appropriate values of the named item.](https://figures.cochat.ai/paper-figures/81710f4758fb4297ae738c783a4c25a5/extracting-accurate-materials-data-from-research-papers-with-conversational-figure-3.jpg)
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Although these proof-of-concept studies have reported encouraging results and the potential to substantially reduce manual workload and human error, most evaluations have been limited to single models, small or restricted datasets, or single extraction runs (15–20).”
From Performance of large language models and prompt engineering strategies for data extraction in systematic reviews (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“one study demonstrated that GPT-4 achieved precision and recall approaching 90% for automated extraction of structured scientific data using prompt-engineered workflows (18).”
From Performance of large language models and prompt engineering strategies for data extraction in systematic reviews (2026) · cites this paper as [18]
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
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
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302 · cited 2×
“Prompt engineering has now become a standard practice in the field of image generation [32–34] to ensure high quality results.”
BackgroundKaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,690
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis
Ong, S. P., Richards, W. D., Jain, A., Hautier, G., Kocher, M., Cholia, S., Gunter, D., Chevrier, V. L., Persson, K. A., & Ceder, G. (2013) · Computational Materials Science · doi:10.1016/j.commatsci.2012.10.028 · Cited by 4,534
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
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604 · cited 1×
“As an alternative model to assess, we chose LLaMA2-chat (70B) [39], a model developed by GenAI (Meta), which has extensive documentation [40], and is available to download for free and use locally without limits.”
MethodHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511
Large language models are zero-shot reasoners
Kojima, T., Gu, S. (., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1613 · Cited by 2,013
Large Language Models are Zero-Shot Reasoners
Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11916 · Cited by 2,013
Cited by
Summary of ChatGPT-Related research and perspective towards the future of large language models
Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., He, H., Li, A., He, M., Liu, Z., et al. (2023) · Meta-Radiology · doi:10.1016/j.metrad.2023.100017 · Cited by 855
“Polak et al. [76] proposed ChatExtract method - consisting of a set of engineering prompts applied to a conversational LLM - for automatic data extraction.”
MethodPrompt Engineering in Large Language Models
Marvin, G., Hellen, N., Jjingo, D., & Nakatumba-Nabende, J. (2024) · Algorithms for Intelligent Systems · doi:10.1007/978-981-99-7962-2_30 · Cited by 403
Kang, Y., & Kim, J. (2024) · Nature Communications · doi:10.1038/s41467-024-48998-4 · Cited by 236
Korzynski, P., Mazurek, G., Krzypkowska, P., & Kurasinski, A. (2023) · Entrepreneurial Business and Economics Review · doi:10.15678/eber.2023.110302 · Cited by 235
“Science – data extraction: Polak and Morgan (2023) proposed the ChatExtract method using engi‐ neered prompts applied to a conversational LLM for accurate data extraction from research articles.”
MethodArtificial Intelligence for Materials Discovery, Development, and Optimization
Madika, B., Saha, A., Kang, C., Buyantogtokh, B., Agar, J., Wolverton, C. M., Voorhees, P., Littlewood, P., Kalinin, S., & Hong, S. (2025) · ACS Nano · doi:10.1021/acsnano.5c04200 · Cited by 171
Metadata
- Authors
- Polak, M. P., & Morgan, D.
- Affiliations
- University of Wisconsin–Madison (US)
- Corresponding author
- Polak, Maciej P.
- Morgan, Dane
- Venue
- Nature Communications
- Published
- 2024-02-21
- Volume
- 15
- Issue
- 1
- Pages
- 1569-1569
- ISSN
- 2041-1723 (ISSN-L)
- PMC
- PMC10882009
- OpenAlex
- W4392002118
- Cited by
- 365
- References
- 40
- Citations by year
- 2026: 136 · 2025: 156 · 2024: 70
- FWCI
- 35.33
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Nature Communications (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- National Science Foundation (1931298)
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Keywords
- automated data extraction, research papers, prompt engineering, materials data, factual accuracy, amorphous alloys, critical cooling rate, high-entropy alloys, yield strength, information retention
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Extracting accurate materials data from research papers with conversational language models and prompt engineering. https://app.cochat.ai/papers/10.1038/s41467-024-45914-8
- The paper
- Polak, M. P., & Morgan, D. (2024). Extracting accurate materials data from research papers with conversational language models and prompt engineering. Nature Communications. https://doi.org/10.1038/s41467-024-45914-8
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.