Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information
This work addresses the challenge of effective information elicitation and retrieval in the specialized domain of nuclear fusion energy, which is incremental as it applies existing methods to a new dataset.
The paper tackles the problem of structuring domain-specific knowledge from large document corpora by constructing the first knowledge graph for nuclear fusion energy, using a multi-step approach that includes automated named entity recognition and entity resolution with pre-trained large language models, and develops a retrieval-augmented generation system for answering complex queries.
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.