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

Koushik Rameshbabu; Jing Luo; Ali Shargh; Khalid A. El-Awady; Jaafar A. El-Awady

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

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 Field	Symbol
Metal Symbol	–
Sample ID	–
Synthesis Method	–
Treatment	–
Initial Temperature (K)	$T_{0}$
Quasi-static Yield Stress (MPa)	$\sigma_{y}$

Table 1: List of the 37 extracted fields defining the spall-strength dataset schema.

Class	Rule Name	Description
Interpretation & Normalization	A. Symbol Disambiguation	Resolves ambiguous symbols to physical quantities
	B. Uncertainty Extraction	Preserves original error formats (e.g., $\pm$ , parenthesis)
Extraction Strategy & Priority	C. Data Priority	Define prioritization of extraction sources: Direct $\rightarrow$ Calculated $\rightarrow$ Figure
	D. Record Identification and Grouping	Identify and extract parameters from text or tables
	E. Figure Extraction	Apply centroid logic to digitize data points from figures
Physics Constraints & Derivations	F. Unit Conversion	Enforce canonical units across all output fields

Table 2: Operational rules for guiding the data extraction process, grouped by class.

Parameter	Formula (in SI units)
Longitudinal stress at HEL	$\displaystyle\sigma_{\text{HEL}}=0.5\,\rho_{0}\,c_{L}\,u_{\text{HEL}}$
Shear stress at HEL	$\displaystyle\tau_{\text{HEL}}=\left(\frac{c_{s}}{c_{L}}\right)^{2}\,\sigma_{\text{HEL}}$
Spall strength	$\displaystyle\sigma_{\text{sp}}=0.5\,\rho_{0}\,c_{b}\,\Delta u_{\text{pb}}$
Bulk sound speed	$\displaystyle c_{b}=\sqrt{\,c_{L}^{2}-\frac{4}{3}c_{s}^{2}\,}$
Shear modulus	$\displaystyle G=\rho_{0}\,c_{s}^{2}$
Bulk modulus	$\displaystyle B=\rho_{0}\,c_{b}^{2}$

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%.

Panel of Figure 5 — 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.

Document Information Extraction

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

See all 279 papers

Large language model-enabled automated data extraction for concrete materials informatics
Apr 24, 2026Zhanzhao Li, Kengran Yang, Qiyao He +1LLM Information Extraction
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
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
Aug 19, 2026Valentin Romanov, Monique Bax, Steven NiedererLLM Information Extraction LLM Reliability
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
Material Database Agent: A Multimodal Agentic Framework for Scientific Literature Mining
May 5, 2026Achuth Chandrasekhar, Omid Barati Farimani, Radheesh Sharma Meda +1Multi-Agent LLM Systems Document Information Extraction
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

Apr 24, 2026J/K move · Enter open · S save

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

Zhanzhao Li, Kengran Yang, Qiyao He, Kai Gong

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

Open paper AskPDF arXiv

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

F_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.

Abstract

Document Information Extraction

Explore similar work

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

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

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