Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment
Researchers have developed CS-VAR, a novel system designed to detect risks like scams and malicious behavior in live streaming platforms. This system utilizes retrieval-augmented Large Language Models (LLMs) to analyze evidence across different streaming sessions, identifying recurring patterns that might otherwise go unnoticed. CS-VAR employs a two-tiered approach, with a lightweight model performing fast, real-time risk inference guided by the LLM's broader insights, enabling efficient and interpretable moderation. AI
IMPACT Introduces a novel method for real-time risk detection in live streaming, potentially improving platform safety and user experience.