From Papers to Property Tables: A Priority-Based LLM Workflow for Materials Data Extraction
2026-04-08 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed an automated method using a large language model to gather detailed experimental data from scientific papers about shock physics, focusing on alloy spall strength. Their process collects information from text, tables, figures, and physics equations in a structured way, checks the data for consistency, and labels each data point by its extraction method. Tested on many articles, their method showed high accuracy, especially when extracting directly from text and tables or using physics formulas. This tool can help scientists quickly build accurate databases from scattered and complex research reports without needing special adjustments.
large language modeldata extractionshock physicsalloy spall strengthphysics-based derivationdigitizationdata normalizationscientific literatureaccuracy evaluationdatabase construction
Authors
Koushik Rameshbabu, Jing Luo, Ali Shargh, Khalid A. El-Awady, Jaafar A. El-Awady
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.