LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection

2026-08-19

AI Summary

本文提出了一种基于大语言模型的表格异常检测方法LLM-Detector，通过利用上下文学习能力从结构化正常状态知识中推导出异常检测逻辑，无需微调或训练神经网络。

Abstract

Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations. Existing detectors rely on geometric or reconstruction signals, while prior LLM-based approaches mainly fine-tune LLMs with normal samples or generate synthetic anomalies. We propose LLM-Detector, 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. Specifically, normal training data are converted into statistical summaries, causal dependencies, and distilled prototypes that are organized into a prompt for code generation. The resulting scoring engine evaluates statistical deviation, structural inconsistency, and density-based abnormality then computes an anomaly score for each test sample. We evaluate LLM-Detector on 24 tabular datasets, comparing against 15 SOTA baselines. Results show consistent improvements across both mixed-type and continuous-only settings. Moreover, this design eliminates the need for LLM fine-tuning or neural network training, reducing computational cost and enabling practical anomaly detection in real-world tabular systems.

Problem

• anomaly detection
• tabular data
• cross-feature dependencies

Innovation

• in-context learning
• tabular anomaly detection
• statistical summaries
• causal dependencies
• prototype distillation