• Home
  • Search
  • Utilizing Large Language Models for Geoscience Literature Information Extraction
  • Cite Icon1
  • https://doi.org/10.5194/egusphere-egu24-16101Copy DOI Icon

Utilizing Large Language Models for Geoscience Literature Information Extraction

  • Jan 20, 2025
  • Peng Yu +3 more
Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Extracting information from unstructured and semi-structured geoscience literature is a crucial step in conducting geological research. The traditional machine learning extraction paradigm requires a substantial amount of high-quality manually annotated data for model training, which is time-consuming, labor-intensive, and not easily transferable to new fields. Recently, large language models (LLMs) (e.g., ChatGPT, GPT-4, and LLaMA), have shown great performance in various natural language processing (NLP) tasks, such as question answering, machine translation, and text generation. A substantial body of work has demonstrated that LLMs possess strong in-context learning (ICL) and even zero-shot learning capabilities to solve downstream tasks without specifically designed supervised fine-tuning. In this paper, we propose utilizing LLMs for geoscience literature information extraction. Specifically, we design a hierarchical PDF parsing pipeline and an automated knowledge extraction process, which can significantly reduce the need for manual data annotation, assisting geoscientists in literature data mining. For the hierarchical PDF parsing pipeline, firstly, a document layout detection model fine-tuned on geoscience literature is employed for layout detection, obtaining layout detection information for the document. Secondly, based on the document layout information, an optical character content parsing model is used for content parsing, obtaining the text structure and plain text corresponding to the content. Finally, the text structure and plain text are combined and reconstructed to ultimately obtain the parsed structured data. For the automated knowledge extraction process, firstly, the parsed long text is segmented into paragraphs to adapt to the input length limit of LLMs. Subsequently, a few-shot prompting method is employed for structured knowledge extraction, encompassing two tasks: attribute value extraction and triplet extraction. In attribute value extraction, prompts are generated automatically by the LLMs based on the subdomain and attribute names, facilitating the location and extraction of values related to subdomain attribute names in the text. For triplet extraction, the LLMs employ a procedural approach to entity extraction, entity type extraction, and relation extraction, following the knowledge graph structure pattern. Finally, the extracted structured knowledge is stored in the form of knowledge graphs, facilitating further analysis and integration of various types of knowledge from the literature. Our proposed approach turns out to be simple, flexible, and highly effective in geoscience literature information extraction. Demonstrations of information extraction in subdomains such as radiolarian fossils and fluvial facies have yielded satisfactory results. The extraction efficiency has significantly improved, and feedback from domain experts indicates a relatively high level of accuracy in the extraction process. The extracted results can be used to construct a foundational knowledge graph for geoscience literature, supporting the comprehensive construction and efficient application of a geoscience knowledge graph.

Similar Papers
  • Research Article

Influence of Knowledge Extraction Methods on the Effectiveness of Graph-Based Rag Systems

  • Nov 26, 2025
  • NaUKMA Research Papers. Computer Science
  • Maksym Androshchuk
  • Front Matter
  • Citations1

Editorial: Large language models in work and business.

  • Nov 29, 2024
  • Frontiers in artificial intelligence
  • Şadi Evren Şeker
  • Book Chapter
  • Citations2

Enhancing Manufacturing Knowledge Access with LLMs and Context-Aware Prompting

  • Oct 16, 2024
  • Frontiers in artificial intelligence and applications
  • Sebastian Monka +6
  • Research Article

Evaluating gpt-4 for zero-shot classification of bleeding and clotting events: Can large language models serve as second reviewers?

  • Nov 03, 2025
  • Blood
  • Samantha Rizzo +5
  • Research Article
  • Citations3

ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training

  • Oct 24, 2025
  • ACM Transactions on Asian and Low-Resource Language Information Processing
  • Jiayang Wu +3
  • Research Article

#2924 Comparison of large language models and traditional natural language processing techniques in predicting arteriovenous fistula failure

  • May 23, 2024
  • Nephrology Dialysis Transplantation
  • Suman Lama +6
  • Conference Article
  • Citations4

Knowledge graph Extraction from Textual data using LLM

  • Jan 01, 2024
  • Research Article
  • Citations65

Model tuning or prompt Tuning? a study of large language models for clinical concept and relation extraction

  • Mar 26, 2024
  • Journal of Biomedical Informatics
  • Cheng Peng +6
  • Research Article
  • Citations26

Knowledge graph–based thought: a knowledge graph–enhanced LLM framework for pan-cancer question answering

  • Jan 06, 2025
  • GigaScience
  • Yichun Feng +5
  • Research Article
  • Citations51

Large language models for biomedicine: foundations, opportunities, challenges, and best practices.

  • Apr 24, 2024
  • Journal of the American Medical Informatics Association : JAMIA
  • Satya S Sahoo +8
  • Research Article
  • Citations21

KNowNEt:Guided Health Information Seeking from LLMs via Knowledge Graph Integration.

  • Jan 01, 2025
  • IEEE transactions on visualization and computer graphics
  • Youfu Yan +4
  • Conference Article

Quantifying Informativeness in Knowledge Graph-Augmented In-Context Learning for Multiple Choice Query Answering

  • Nov 13, 2025
  • Maryam Ghanbari +1
  • Research Article
  • Citations1

Enhancing Knowledge Graph Construction with Automated Source Evaluation Using Large Language Models

  • Apr 28, 2025
  • JUCS - Journal of Universal Computer Science
  • Hendrik Hendrik +2
  • Research Article

HIEA: Hierarchical Inference for Entity Alignment with Collaboration of Instruction-Tuned Large Language Models and Small Models

  • Jan 18, 2026
  • Electronics
  • Xinchen Shi +2
  • Conference Article
  • Citations16

HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs

  • Jan 01, 2024
  • Pranoy Panda +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.