作为检测器的大语言模型：一种用于表格异常检测的上下文学习方法
LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection
浏览论文内容
中文总结 AI 辅助
本研究提出LLM-Detector框架，利用LLM的上下文学习能力进行表格异常检测，在24个数据集上对比15个SOTA基线均获提升，且无需微调或神经网络训练，降低了计算成本。
中文摘要 AI 辅助
表格数据的异常检测颇具挑战性，因为异常样本往往源于跨特征依赖关系的违反，而非单纯的边际偏差。现有检测器依赖几何或重构信号，而此前基于大语言模型（LLM）的方法主要通过正常样本微调LLM或生成合成异常。我们提出LLM-Detector框架，该框架利用LLM的上下文学习能力进行结构化、提示条件化的评分合成，使LLM能从结构化正常状态知识中推导异常检测逻辑。具体而言，将正常训练数据转换为统计摘要、因果依赖关系及提炼的原型，这些内容被组织成用于代码生成的提示。所得评分引擎评估统计偏差、结构不一致性及基于密度的异常，随后为每个测试样本计算异常分数。我们在24个表格数据集上对LLM-Detector进行评估，与15个当前最优（SOTA）基线方法对比。结果显示，其在混合类型及仅连续类型的设置中均表现出持续的性能提升。此外，该设计无需进行LLM微调或神经网络训练，降低了计算成本，可在实际表格系统中实现实用的异常检测。
英文摘要
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.
发表机构
- Applied Artificial Intelligence Initiative (A2I2), Deakin University（应用人工智能计划（A2I2），迪肯大学）
- Adelaide University（阿德莱德大学）
- Monash University（莫纳什大学）
机构由 AI 辅助整理，请以论文原文为准。
