paper-with-me

홈 › Papers

Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information

2025-04-10 · A. Loreti, K. Chen, R. George, R. Firth, A. Agnello, S. Tanaka

In this document, we discuss a multi-step approach to automated construction of a knowledge graph, for structuring and representing domain-specific knowledge from large document corpora. We apply our method to build the first knowledge graph of nuclear fusion energy, a highly specialized field characterized by vast scope and heterogeneity. This is an ideal benchmark to test the key features of our pipeline, including automatic named entity recognition and entity resolution. We show how pre-trained large language models can be used to address these challenges and we evaluate their performance against Zipf's law, which characterizes human-generated natural language. Additionally, we develop a knowledge-graph retrieval-augmented generation system that combines large language models with a multi-prompt approach. This system provides contextually relevant answers to natural-language queries, including complex multi-hop questions that require reasoning across interconnected entities.

📄 PDF Abstract BibTeX arXiv:2504.07738

Code (0)

등록된 구현이 없습니다.

Tasks

Entity Resolutionnamed-entity-recognitionNamed Entity RecognitionNatural Language QueriesRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models

2026-06-25 · Henry Shaowu Yuchi, Michal Kucer, Benjamin H. Sims, Selma Peterson 외 arxiv

Large language models (LLMs) have demonstrated strong performance across a wide range of tasks, but ensuring their reliability in highly technical domains remains a significant challenge. In nuclear engineering, problem …

Question Generation

Deep Learning for Plasma Tomography in Nuclear Fusion

2020-10-23 · Diogo R. Ferreira, Pedro J. Carvalho

Tomography is arguably one of the most representative examples of an inverse problem, where the shape of an object must be reconstructed from its projections over a limited number of lines of sight. The regularization th…

Deep Learning

Double-Constraint Diffusion Model with Nuclear Regularization for Ultra-low-dose PET Reconstruction

2025-08-30 · Mengxiao Geng, Ran Hong, Bingxuan Li, Qiegen Liu arxiv

Ultra-low-dose positron emission tomography (PET) reconstruction holds significant potential for reducing patient radiation exposure and shortening examination times. However, it may also lead to increased noise and redu…

Information Extraction

DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidation

2025-07-09 · Qingsong Yang, Binglan Wu, Xuwei Liu, Bo Chen 외 arxiv

Nuclear Magnetic Resonance (NMR) spectroscopy is a central characterization method for molecular structure elucidation, yet interpreting NMR spectra to deduce molecular structures remains challenging due to the complexit…

Contrastive Learning

Automated Scoring of Nuclear Pleomorphism Spectrum with Pathologist-level Performance in Breast Cancer

2020-12-09 · Caner Mercan, Maschenka Balkenhol, Roberto Salgado, Mark Sherman 외

Nuclear pleomorphism, defined herein as the extent of abnormalities in the overall appearance of tumor nuclei, is one of the components of the three-tiered breast cancer grading. Given that nuclear pleomorphism reflects …

whole slide images