LLMs using few-shot in-context learning on serialized k-hop subgraphs from synthetic AML scenarios can assess suspiciousness and generate natural-language justifications.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exploring the In-Context Learning Capabilities of LLMs for Money Laundering Detection in Financial Graphs
LLMs using few-shot in-context learning on serialized k-hop subgraphs from synthetic AML scenarios can assess suspiciousness and generate natural-language justifications.