A RAG-based LLM pipeline classifies phone calls as fraudulent by comparing transcripts against company policy documents, with a reported 97.98% accuracy on synthetic calls.
Fraud loss survey
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Advanced Real-Time Fraud Detection Using RAG-Based LLMs
A RAG-based LLM pipeline classifies phone calls as fraudulent by comparing transcripts against company policy documents, with a reported 97.98% accuracy on synthetic calls.