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.

R. Avice, B. Haslhofer, Z. Li, J. Zhou, Linking Cryptoasset Attribution Tags to Knowledge Graph Entities: An LLM-Based Approach, Lecture Notes in Computer Science, Financial Cryptography and Data Security 15752 (2026) 366-382.