LLMs using the new LLM4TG format and CETraS sampling can analyze Bitcoin transaction graphs, achieving high node-level accuracy and 72.43% top-3 few-shot classification accuracy, but remain behind engineered classifiers.
A survey on evaluation of large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Large Language Models for Cryptocurrency Transaction Analysis: A Bitcoin Case Study
LLMs using the new LLM4TG format and CETraS sampling can analyze Bitcoin transaction graphs, achieving high node-level accuracy and 72.43% top-3 few-shot classification accuracy, but remain behind engineered classifiers.