Linking Cryptoasset Attribution Tags to Knowledge Graph Entities: An LLM-based Approach

TL;DR

This paper presents an LLM-based method to accurately link cryptoasset attribution tags to knowledge graph entities, improving forensic reliability and reducing costs.

Contribution

It introduces a novel computational pipeline that outperforms baseline methods, achieves high recall without labeled data, and analyzes cost-performance trade-offs of LLM configurations.

Findings

Outperforms baseline methods by up to 37.4% in F1-score

Achieves 93% recall with candidate sets of five entities

Local LLM models reach 90% F1-score, close to remote models' 94%

Abstract

Attribution tags form the foundation of modern cryptoasset forensics. However, inconsistent or incorrect tags can mislead investigations and even result in false accusations. To address this issue, we propose a novel computational method based on Large Language Models (LLMs) to link attribution tags with well-defined knowledge graph concepts. We implemented this method in an end-to-end pipeline and conducted experiments showing that our approach outperforms baseline methods by up to 37.4% in F1-score across three publicly available attribution tag datasets. By integrating concept filtering and blocking procedures, we generate candidate sets containing five knowledge graph entities, achieving a recall of 93% without the need for labeled data. Additionally, we demonstrate that local LLM models can achieve F1-scores of 90%, comparable to remote models which achieve 94%. We also analyze the cost-performance trade-offs of various LLMs and prompt templates, showing that selecting the most cost-effective configuration can reduce costs by 90%, with only a 1% decrease in performance. Our method not only enhances attribution tag quality but also serves as a blueprint for fostering more reliable forensic evidence.