Preprint
Aug 2026
LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection
LLM-Detector is proposed, a framework that utilizes the in-context learning capacity of LLMs for structured, prompt-conditioned scoring synthesis, enabling LLMs to derive anomaly detection logic from structured normal-state knowledge.
Tu Nguyen, Dang Nguyen, T. Le et al.
· 0 citations