Knowledge Graph Enrichment and Reasoning for Nobel Laureates

TL;DR

This paper constructs an enriched knowledge graph of Nobel Laureates using LLMs for data augmentation, social network analysis, and develops a chatbot for natural language querying, demonstrating effective reasoning and pattern discovery.

Contribution

It introduces a novel integration of LLM-based data enrichment, social network analysis, and a Text2Cypher chatbot for complex reasoning over a Nobel Laureates knowledge graph.

Findings

The enriched graph exhibits small-world network properties.

The chatbot achieves high accuracy on a custom evaluation dataset.

The approach uncovers hidden influential figures and organizations.

Abstract

This project aims to construct and analyze a comprehensive knowledge graph of Nobel Prize and Laureates by enriching existing datasets with biographical information extracted from Wikipedia. Our approach integrates multiple advanced techniques, consisting of automatic data augmentation using LLMs for Named Entity Recognition (NER) and Relation Extraction (RE) tasks, and social network analysis to uncover hidden patterns within the scientific community. Furthermore, we also develop a GraphRAG-based chatbot system utilizing a fine-tuned model for Text2Cypher translation, enabling natural language querying over the knowledge graph. Experimental results demonstrate that the enriched graph possesses small-world network properties, identifying key influential figures and central organizations. The chatbot system achieves a competitive accuracy on a custom multiple-choice evaluation dataset, proving the effectiveness of combining LLMs with structured knowledge bases for complex reasoning tasks. Data and source code are available at: https://github.com/tlam25/network-of-awards-and-winners.