Sub-field · 15 papers
LLM Scientific Literature Processing
Applying large language models (LLMs) and retrieval-augmented generation (RAG) to scientific and digital library document processing is the central focus, encompassing tasks such as information extraction, summarization, hypothesis and limitation identification, and definition generation from research literature. Methods span prompt engineering, graph-based approaches, topic modeling, and RAG pipelines applied to specialized corpora including biomedical texts, historical newspapers, and Arabic digital libraries. A recurring sub-theme is enhancing the discoverability and analysis of scholarly content through automated NLP techniques integrated with traditional information retrieval systems.
Papers in this community
- LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations 2024 DOI ↗
- Generating Suggestive Limitations from Research Articles Using LLM and Graph-Based Approach 2024 DOI ↗
- A review on knowledge and information extraction from PDF documents and storage approaches 2025 DOI ↗
- A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models 2024 DOI ↗
- Retrieval Augmented Generation for Historical Newspapers 2024 DOI ↗
- Navigating Nuance: In Quest for Political Truth 2024 DOI ↗
- Leveraging LLMs for Scientific Abstract Summarization: Unearthing the Essence of Research in a Single Sentence 2024 DOI ↗
- From Static to Dynamic: Survey-based Academic Impact Measurement 2024 DOI ↗
- Exploring Efficient Optimization Techniques in Online Retrieval-Augmented Generation Application 2024 DOI ↗
- Enhancing Digital Libraries with Automated Definition Generation 2024 DOI ↗
- Enhancing Biomedical Literature Retrieval with Level of Evidence and Bio-Concepts: A Comparative User Study 2024 DOI ↗
- Can LLMs categorize the specialized documents from web archives in a better way? 2024 DOI ↗
- Arabic Text Enhancement with GPT for Digital Libraries 2024 DOI ↗
- A Cross-Cultural Framework for Detecting Public Opinion about AI Ethics 2024 DOI ↗
- Using Large Language Models for Hypotheses and Claims Extraction from Scientific Literature 2025 DOI ↗