Text Mining for Process–Structure–Properties Relationships in Metals

Journal Article · Fri Sep 26 00:00:00 EDT 2025 · Integrating Materials and Manufacturing Innovation

DOI:https://doi.org/10.1007/s40192-025-00420-7· OSTI ID:3014104

Verma, Amit K. ^[1]; Zhang, Zhisong ^[2]; Seo, Junwon ^[2]; Kuo, Robin ^[2]; Jiang, Runbo ^[2]; Strubell, Emma ^[2]; Rollett, Anthony D. ^[2]

---

1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
2. Carnegie Mellon Univ., Pittsburgh, PA (United States)

With the advent of large language models (LLMs), the vast unstructured text within millions of academic papers is increasingly accessible for materials discovery—although significant challenges remain. While LLMs offer promising few- and zero-shot learning capabilities, particularly valuable in the materials domain where expert annotations are scarce, general-purpose LLMs often fail to address key materials-specific queries without further adaptation. To bridge this gap, fine-tuning LLMs on human-labeled data is essential for effective structured knowledge extraction (Liu in The Importance of Human-Labeled Data in the Era of LLMs, 2023). Here, in this study, we introduce a novel annotation schema designed to extract generic process–structure–properties relationships from scientific literature. We demonstrate the utility of this approach using a dataset of 128 abstracts, with annotations drawn from two distinct domains: high-temperature materials (Domain I) and uncertainty quantification in simulating materials microstructure (Domain II). Initially, we developed a conditional random field (CRF) model based on MatBERT—a domain-specific BERT variant—and evaluated its performance on Domain I. Subsequently, we compared this model with a fine-tuned LLM (GPT-4o from OpenAI) under identical conditions. Our results indicate that fine-tuning LLMs can significantly improve entity extraction performance over the BERT-CRF baseline on Domain I. However, when additional examples from Domain II were incorporated, the performance of the BERT-CRF model became comparable to that of the GPT-4o model. These findings underscore the potential of our schema for structured knowledge extraction and highlight the complementary strengths of both modeling approaches.

• Research Organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
• Sponsoring Organization: US Army Research Laboratory (USARL); USDOE National Nuclear Security Administration (NNSA)
• Grant/Contract Number: AC52-07NA27344
• OSTI ID: 3014104
• Report Number(s): LLNL--JRNL-2011378
• Journal Information: Integrating Materials and Manufacturing Innovation, Journal Name: Integrating Materials and Manufacturing Innovation Journal Issue: 4 Vol. 14; ISSN 2193-9764; ISSN 2193-9772
• Publisher: Springer
• Country of Publication: United States
• Language: English

Related Subjects

Materials science