Forecasting Research Trends Using Knowledge Graphs and Large Language Models
Name
Advanced Intelligent Systems - 2025 - Tomczak - Forecasting Research Trends Using Knowledge Graphs and Large Language.pdf
Description
Published version
Size
5.99 MB
Format
Adobe PDF
Checksum (MD5)
d999d257f71c3f6c328699f33167af9d
Author(s)
Tomczak, Maciej
Park, Yang Jeong
Hsu, Chia‐Wei
Brown, Payden
Massa, Dario
Sankowski, Piotr
Li, Ju
Papanikolaou, Stefanos
Date Issued
September 12, 2025
Journal
Advanced Intelligent Systems
Publisher
Wiley
Citation
Maciej Tomczak, Yang Jeong Park, Chia-Wei Hsu, Payden Brown, Dario Massa, Piotr Sankowski, Ju Li, Stefanos Papanikolaou. Adv. Intell. Syst.. 2025; 000, e2401124.
Version
Final published version
Abstract
Since ancient times, oracles (e.g., Delphi) has the ability to provide useful visions of where the society is headed, based on key event correlations and educated guesses. Currently, foundation models are able to distill and analyze enormous text-based data that can be used to understand where societal components are headed in the future. This work investigates the use of three large language models (LLM) and their ability to aid the research of nuclear materials. Using a large dataset of Journal of Nuclear Materials papers spanning from 2001 to 2021, models are evaluated and compared with perplexity, similarity of output, and knowledge graph metrics such as shortest path length. Models are compared to the highest performer, OpenAI's GPT-3.5. LLM-generated knowledge graphs with more than 2 × 105 nodes and 3.3 × 105 links are analyzed per publication year, and temporal tracking leads to the identification of criteria for publication innovation, controversy, influence, and future research trends.
MIT Department
Massachusetts Institute of Technology. Department of Nuclear Science and Engineering
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1002/aisy.202401124
