ArticleNature communications2024
Extracting accurate materials data from research papers with conversational language models and prompt engineering.
Article in Nature communications, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 72 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
72 citing papers in PubMed.
- Data-Driven Materials Science for Energy-Sustainable Applications.Advanced materials (Deerfield Beach, Fla.) · 2026Review
- Autogenerating a Domain-Specific Question-Answering Data Set to Enable High-Performing Language Models for Magnetic Materials.Journal of chemical information and modeling · 2026Article
- STDN-GEN: rapid synthesis of layered critical-material dependency networks for supply-chain sustainability analysis.Research square · 2026Article
- Sustainable Polymer Aerogels: Multiscale Design from Biomass and Thermoset Networks to AI-Guided Materials Discovery.Gels (Basel, Switzerland) · 2026Review
- Article
- OmniExtract: an automatic data extraction tool based on large language model and prompt engineering.Briefings in bioinformatics · 2026Article
- Machine Learning-Empowered Electromagnetic Wave Absorbing Materials: From Forward Prediction to Generative Inverse Design.Molecules (Basel, Switzerland) · 2026Review
- Librarian of Alexandria: A Modular Chemical Data Extraction Pipeline to Compare LLM Performance.Journal of chemical information and modeling · 2026Article
- Fine-tuning large language models to generate single-atom catalyst synthesis procedures.Communications chemistry · 2026Article
- Automated Extraction of Multicomponent Alloy Data Using Large Language Models for Sustainable Design.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Evaluating guideline adherence in LLM studies using LLMs.Japanese journal of radiology · 2026Article
- Open-source large language model-based on-premises pipeline for automated data extraction from unstructured electronic health records: a pilot study.BMJ health & care informatics · 2026Article
- Methods to estimate marine functional connectivity: A primer.Ecological applications : a publication of the Ecological Society of America · 2026Review
- Towards generalizable seizure monitoring: EpiVLM for cross-environment detection and classification.NPJ digital medicine · 2026Article
- Rational Design of Single-Phase High-Entropy Oxides via Large Language Model Data Mining and Explainable Machine Learning.Journal of chemical information and modeling · 2026Article
- DxDirector: an agentic large language model driving the full-process clinical diagnosis.Nature communications · 2026Article
- From LLMs to AI agents: a systematic benchmark for SAO structure extraction in patent analytics.Scientific reports · 2026Article
- Sustainable Materials Design With Multi-Modal Artificial Intelligence.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Review
- Towards a sustainable high-quality materials data ecosystem: frameworks and strategies.National science review · 2026Review
- Large Language Models in Injury Prediction Tools: Simplifying User Interactions and Improving Risk Interpretation.Annals of biomedical engineering · 2026Article
12 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
Abstract
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 ChatExtract method that can fully automate very accurate data extraction with minimal initial effort and background, using an advanced conversational LLM. ChatExtract 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. ChatExtract 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 ChatExtract, 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 ChatExtract.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.