Sub-field · 23 papers
Scientific Document Analysis and Mining
Scholarly information extraction, organization, and analysis in digital libraries form the core focus, using methods ranging from large language models and retrieval-augmented generation to graph-based representations and fine-tuned transformers. Tasks addressed include citation analysis, software and dataset mention detection, paper source tracing, novelty measurement, and scientific synthesis across biomedical, humanities, and historical document domains. A recurring sub-theme is benchmarking and tooling for measuring innovation and methodology evolution within the scientific literature itself.
Papers in this community
- JCDL2024Workshop: The 2nd Workshop on Innovation Measurement for Scientific Communication (IMSC) in the Era of Big Data 2024 DOI ↗
- RAGing Against the Literature: LLM-Powered Dataset Mention Extraction 2024 DOI ↗
- Fast Bibliography Pre-Selection via Two-Vector Semantic Representations 2024 DOI ↗
- Requirements for a Digital Library System: A Case Study in Digital Humanities 2024 DOI ↗
- Which Types of Word Embedding Models are More Effective for Novelty Measurement? 2024 DOI ↗
- Unlocking Scholarly Insights: Leveraging Machine Learning Approaches for Citation Analysis and Intent Classification. 2024 DOI ↗
- Training a Geographic Entity Recognizer on Biomedical Abstracts with the Aid of Embeddings, Metadata, and Linked Data 2024 DOI ↗
- Seventeenth-Century Spanish American Notary Records for Fine-Tuning Spanish Large Language Models 2024 DOI ↗
- Measuring the Novelty of Scientific Papers Based on the Latent Distance Between Pairs of MeSH Terms 2024 DOI ↗
- MPR: A Dataset for Extracting Relations Between Method Entities and Scientific Papers 2024 DOI ↗
- LLMs4Synthesis: Leveraging Large Language Models for Scientific Synthesis 2024 DOI ↗
- KNITTIR: Syntactical Text Indexing for Analytics 2024 DOI ↗
- InfoTrace: A System for Information Campaign Source Tracing and Analysis on Social Media 2024 DOI ↗
- Identifying and classifying software mentions in full text scholarly documents 2025 DOI ↗
- Disaster Image Tagging Using Generative AI for Digital Archives 2024 DOI ↗
- DBRP: Decomposition and Branch Reasoning Improves Paper Source Tracing 2024 DOI ↗
- Construction of Data Mining Platform for Ancient Chinese Agricultural Books Bibliographic Summaries 2024 DOI ↗
- Citation-Worthy Detection of URL Citations in Scholarly Papers 2024 DOI ↗
- Chronological Evaluation of Novel Methodology Extraction from AI Literature 2024 DOI ↗
- A Library Perspective on Supervised Text Processing in Digital Libraries: An Investigation in the Biomedical Domain 2024 DOI ↗
- A Comparative Study of Algorithm Usage in Library and Information Science Research: China vs. Other Countries 2024 DOI ↗
- LitFM: A Retrieval Augmented Structure-aware Foundation Model For Citation Graphs 2025 DOI ↗
- CSI-Chain: A Complete End-to-End Framework for WiFi CSI Sensing 2026 DOI ↗