cs.AIApr 8, 2026

From Papers to Property Tables: A Priority-Based LLM Workflow for Materials Data Extraction

Authors: Koushik Rameshbabu, Jing Luo, Ali Shargh, Khalid A. El-Awady, Jaafar A. El-Awady

Organizations: Department of Applied Mathematics and Statistics, Johns Hopkins University · Department of Mechanical Engineering, Johns Hopkins University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Scientific data are widely dispersed across research articles and are often reported inconsistently across text, tables, and figures, making manual data extraction and aggregation slow and error-prone. We present a prompt-driven, hierarchical workflow that uses a large language model (LLM) to automatically extract and reconstruct structured, shot-level shock-physics experimental records by integrating information distributed across text, tables, figures, and physics-based derivations from full-text published research articles, using alloy spall strength as a representative case study. The pipeline targeted 37 experimentally relevant fields per shot and applied a three-level priority strategy: (T1) direct extraction from text/tables, (T2) physics-based derivation using verified governing relations, and (T3) digitization from figures when necessary. Extracted values were normalized to canonical units, tagged by priority for traceability, and validated with physics-based consistency and plausibility checks. Evaluated on a benchmark of 30 published research articles comprising 11,967 evaluated data points, the workflow achieved high overall accuracy, with priority-wise accuracies of 94.93% (T1), 92.04% (T2), and 83.49% (T3), and an overall weighted accuracy of 94.69%. Cross-model testing further indicated strong agreement for text/table and equation-derived fields, with lower agreement for figure-based extraction. Implementation through an API interface demonstrated the scalability of the approach, achieving consistent extraction performance and, in a subset of test cases, matching or exceeding chat-based accuracy. This workflow demonstrates a practical approach for converting unstructured technical literature into traceable, analysis-ready datasets without task-specific fine-tuning, enabling scalable database construction in materials science.

Figures & tables

Figure 1: Prompt-development and refinement workflow for LLM-based data extraction from documents.
Extracted FieldSymbol
Metal Symbol–
Sample ID–
Synthesis Method–
Treatment–
Initial Temperature (K)T0T_{0}
Quasi-static Yield Stress (MPa)σy\sigma_{y}
Table 1: List of the 37 extracted fields defining the spall-strength dataset schema.
ClassRule NameDescription
Interpretation & NormalizationA. Symbol DisambiguationResolves ambiguous symbols to physical quantities
 B. Uncertainty ExtractionPreserves original error formats (e.g., ±\pm , parenthesis)
Extraction Strategy & PriorityC. Data PriorityDefine prioritization of extraction sources: Direct →\rightarrow Calculated →\rightarrow Figure
 D. Record Identification and GroupingIdentify and extract parameters from text or tables
 E. Figure ExtractionApply centroid logic to digitize data points from figures
Physics Constraints & DerivationsF. Unit ConversionEnforce canonical units across all output fields
Table 2: Operational rules for guiding the data extraction process, grouped by class.
ParameterFormula (in SI units)
Longitudinal stress at HELσHEL=0.5 ρ0 cL uHEL\displaystyle\sigma_{\text{HEL}}=0.5\,\rho_{0}\,c_{L}\,u_{\text{HEL}}
Shear stress at HELτHEL=(cscL)2 σHEL\displaystyle\tau_{\text{HEL}}=\left(\frac{c_{s}}{c_{L}}\right)^{2}\,\sigma_{\text{HEL}}
Spall strengthσsp=0.5 ρ0 cb Δupb\displaystyle\sigma_{\text{sp}}=0.5\,\rho_{0}\,c_{b}\,\Delta u_{\text{pb}}
Bulk sound speedcb= cL2−43cs2 \displaystyle c_{b}=\sqrt{\,c_{L}^{2}-\frac{4}{3}c_{s}^{2}\,}
Shear modulusG=ρ0 cs2\displaystyle G=\rho_{0}\,c_{s}^{2}
Bulk modulusB=ρ0 cb2\displaystyle B=\rho_{0}\,c_{b}^{2}
Table 3: Physics-based relationships utilized for Tier 2 calculations.
Figure 2: Example evidence log for Tier 1 (direct), Tier 2 (calculated), and Tier 3 (figure) extractions.
Figure 3: Weighted average extraction accuracy by article and aggregated at all extraction tiers using Gemini 3 Pro.
Figure 4: Accuracy for each extraction tier using Gemini 3 Pro for all articles combined. The overall weighted average is 94.69%.
Figure 5: Examples of figure-based extraction errors. (a) Small axis-title font can cause the LLM to misread the multiplier. Plot adopted from [ 61 ] with permission. (b) Overlapping open-circle markers can cause the LLM to assign a plotted value to the wrong data point. Plot adopted from [ 32 ] with permission.
Figure 6: Weighted closeness score for Claude Opus 4.5 vs Gemini 3 Pro for all the papers.
Figure 7: The closeness score for each extraction tier between Claude Opus 4.5 and Gemini 3 Pro. The weighted average across all three tiers is 88.76%. This is based on data extracted from 30 articles.
More in this topic

Document Information Extraction

Document Information Extraction turns text, tables, forms, and images into structured, searchable data.

See all 279 papers

Explore similar work

CardsList
Apr 24, 2026

Large language model-enabled automated data extraction for concrete materials informatics

The promise of data-driven materials discovery remains constrained by the scarcity of large, high-quality, and accessible experimental datasets. Here, we introduce a generalizable large language model (LLM)-powered pipeline for automated extraction and structuring of materials data from unstructured scientific literature, using concrete materials as a representative and particularly challenging example. The pipeline exhibits robust performance across a broad range of LLMs and achieves an F1F_1 score of up to 0.98 for diverse composition--process--property attributes. Within one hour, it extracts nearly 9,000 high-quality records with over 100 attributes from a corpus screened from more than 27,000 publications, enabling the construction of the largest open laboratory database for blended cement concrete. Machine learning analyses underscore the importance of large, diverse, and information-rich datasets for enhancing both in-distribution accuracy and out-of-distribution generalization to unseen materials. The proposed pipeline is readily adaptable to other materials domains and accelerates the development of scalable data infrastructures for materials informatics.

Zhanzhao Li, Kengran Yang, Qiyao He +1

Department of Civil and Environmental Engineering, Rice University, Houston, TX 77005, USA. · Rice Advanced Materials Institute, Rice University, Houston, TX 77005, USA. · Ken Kennedy Institute, Rice University, Houston, TX 77005, USA. +1

LLM Information Extraction
AskPDF
Aug 19, 2026

Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models

Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of frontier, browser-based large language models (LLMs) to extract highly contextualized information. We demonstrate four escalating workflows, 1) given an expert curated prompt and research articles, most frontier LLMs perform well at data extraction, however can struggle with interpreting scientific context and nuance, 2) given simple instructions, LLMs can author their own prompts which were almost as eNective as expert-written prompts, 3) autonomous discovery of research literature was diNicult, agents either missed or hallucinated references, and 4) LLMs can create new datasets from published guidelines that closely match human-expert judges, but still require a human-in-the-loop. Together, these findings define an auditable division of labour in which experts specify the evidence standard, models cross-check repeated extractions and researchers resolve disputed cases, providing a practical route to scaling scientific data curation without relinquishing expert oversight.

Valentin Romanov, Monique Bax, Steven Niederer

National Heart & Lung Institute, Faculty of Medicine, Imperial College London, United Kingdom · Cambridge Stem Cell Institute, JeDrey Cheah Biomedical Centre, Cambridge Biomedical Campus, University of Cambridge, Cambridge, United Kingdom · Department of Medicine, University of Cambridge, Cambridge, United Kingdom +1

LLM Information ExtractionLLM ReliabilityLLM PromptingAI Agents for Scientific Discovery
AskPDF
May 5, 2026

Material Database Agent: A Multimodal Agentic Framework for Scientific Literature Mining

Materials science workflows rely on structured and unstructured data from the vast body of available scientific literature. However, most of the experimental details remain buried in text, tables, graphs and figures. Thus, constructing databases that incorporate this data is a manual, time-consuming, and hard-to-scale process. Multimodal large language models have made it feasible to extract information from text and scientific figures with high speed and accuracy. This opens the possibility of an AI system that can create production-scale material databases. Material Database Agent (MDA) is a modular, multi-agent system architecture for converting research literature into structured databases. MDA accepts article PDFs as input, which are subsequently processed in parallel into markdown files and figures. Multiple sub-agents read these markdown files and figures in parallel to assemble sub-databases for each paper. These sub-databases are then compiled into a single tabular database by an agent. As opposed to using either a rule-based approach or a single-pass pipeline for extracting information, MDA is a specialized architecture for transforming the literature into a database in the field of materials science. More generally, this study provides a basis for positioning multimodal agentic information extraction as a viable means for constructing next-generation scientific databases from the primary literature.

Achuth Chandrasekhar, Omid Barati Farimani, Radheesh Sharma Meda +1

Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Biomedical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA +2

Multi-Agent LLM SystemsDocument Information ExtractionMaterials Science
AskPDF