Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment
This work proposes CS-VAR, a lightweight, domain-specific model that performs fast session-level risk inference, guided during training by a Large Language Model that reasons over retrieved cross-session behavioral evidence and transfers its local-to-global insights to the small model.
Yi-Ran Qiao, Xiang Ao, Jing Chen et al.
· Annual International ACM SIG... · 2 citations