Research map / Large language models / Retrieval and knowledge
Enhancing Aging Biomarker Research through Large Language Models and Knowledge Graphs (Student Abstract)
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Builds aging biomarker knowledge graphs both from expert-curated NHANES data (KNARM) and from LLM-extracted literature abstracts (OLIVE), and compares them to argue for systematic integration.
Problem
Aging biomarker names and categories are not standardized, and no formal definition of a biomarker exists, which hampers AI research and data analysis in aging.
Approach
Combines an expert-curated knowledge graph built with the KNARM methodology from NHANES biomarker data with an LLM-driven OLIVE workflow that extracts biomarker relations from literature abstracts, then compares the two graphs to motivate integrating LLMs with expert ontologies.
Key results
- The paper reports that LLM-generated knowledge graphs from literature abstracts remain questionable in accuracy, with expert curation of the NHANES-based KG providing higher reliability (qualitative comparison, no numbers reported).
Limitations
- No quantitative evaluation of LLM-generated KG accuracy is reported
- Automated significance testing produced false positives requiring expert correction
- The LLM used for OLIVE is not specified
Experimental setup
Datasets: NHANES scientific literature abstracts
Builds on: KNARM OLIVE
Closest papers by meaning
- Knowledge Graph and Large Language Model for Metabolomics (AAAI 2025 · similarity 0.85)
- Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval (ICLR 2025 · similarity 0.84)
- LLaVA Needs More Knowledge: Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic Pathologies (AAAI 2025 · similarity 0.82)
- KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA (ICLR 2025 · similarity 0.81)
- CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research (NeurIPS 2025 · similarity 0.81)
- CellVerse: Do Large Language Models Really Understand Cell Biology? (NeurIPS 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.