From Papers to Property Tables: A Priority-Based LLM Workflow for Materials Data Extraction
Department of Applied Mathematics and Statistics, Johns Hopkins University(约翰霍普金斯大学应用数学与统计系);Department of Mechanical Engineering, Johns Hopkins University(约翰霍普金斯大学机械工程系)
Koushik Rameshbabu, Jing Luo, Ali Shargh, Khalid A. El-Awady, Jaafar A. El-Awady
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.
Explanova: Automatically Discover Data Insights in N \times M Table via XAI Combined LLM Workflow
Institute for Clarity in Documentation(清晰文档研究所);Inria Paris-Rocquencourt(巴黎-罗克Quantin 国家信息与自动化研究所);Rajiv Gandhi University(拉吉夫·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕尔默研究实验室)
TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models
Hong Kong University of Science and Technology(香港科技大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));South China Normal University(华南师范大学)
CORE-T: COherent REtrieval of Tables for Text-to-SQL
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany(普适知识处理实验室(UKP实验室),计算机科学系 TU Darmstadt 和应用网络安全国家研究中心 ATHENE,德国);Arizona State University(亚利桑那州立大学);University of Pennsylvania(宾夕法尼亚大学)
PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(中国科学技术大学认知智能国家重点实验室);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)
DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering
Institute of Systems Engineering, Academy of Military Sciences(系统工程研究所,军事科学院);School of Information Resource Management, Renmin University of China(信息资源管理学院,中国人民大学)
Ontology-aligned structuring and reuse of multimodal materials data and workflows towards automatic reproduction
Interdisciplinary Centre for Advanced Materials Simulation, Ruhr-Universität Bochum(波鸿鲁尔大学先进材料模拟跨学科中心);Max Planck Institute for Sustainable Materials(马克斯·普朗克可持续材料研究所);BAM Federal Institute for Materials Research and Testing(BAM联邦材料研究与测试研究所)
ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows
School of CS & Key Lab of High Confidence Software Technologies (MOE), Peking University(计算机科学学院及高可信软件技术重点实验室(教育部),北京大学);Academy for Advanced Interdisciplinary Studies, Peking University(先进跨学科研究学院,北京大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);School of Software & Microelectronics, Peking University(软件与微电子学院,北京大学);School of CS & Beijing Key Laboratory of Software and Hardware Cooperative Artificial Intelligence Systems, Peking University(计算机科学学院及北京软件与硬件协同人工智能系统重点实验室,北京大学);Center for Machine Learning Research, Peking University(机器学习研究中心,北京大学)
SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding
The Chinese University of Hong Kong(香港中文大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);New York University(纽约大学);Fudan University(复旦大学);Shanghai Jiao Tong University(上海交通大学);Harbin Institute of Technology(哈尔滨工业大学);JD Explore Academy(京东探索研究院);Centre for Perceptual and Interactive Intelligence (CPII) Limited(感知与交互智能中心(CPII)有限公司)
InvDesMobility: a reliability-gated first-principles feedback framework for closed-loop materials discovery
School of Physics and Key Laboratory of Quantum State Construction and Manipulation (Ministry of Education), Renmin University of China(物理学院和量子态构造与操控重点实验室(教育部) ,中国人民大学)
MetaConfigurator: AI-Assisted RDF Authoring from JSON Data
Institute for Parallel and Distributed Systems, University of Stuttgart(并行与分布式系统研究所,斯图加特大学);Institute of Polymer Chemistry, University of Stuttgart(聚合化学研究所,斯图加特大学);Institute of Biochemistry, University of Stuttgart(生物化学研究所,斯图加特大学)