CausalTAD: 在表格异常检测中向大语言模型注入因果知识
CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection
AI总结：
CausalTAD通过注入因果知识提升表格异常检测性能，采用因果关系重构与加权策略，实验表明优于现有方法。
摘要：
在表格数据中检测异常对于许多实际应用至关重要，例如信用卡欺诈检测。随着大语言模型（LLMs）的快速发展，通过将表格数据转换为文本并微调LLMs，已在表格异常检测中实现了最先进的性能。然而，这些方法在转换过程中随机排列列，没有考虑它们之间的因果关系，这对于准确检测异常至关重要。在本文中，我们提出了CausalTaD，一种将因果知识注入LLMs以进行表格异常检测的方法。我们首先确定列之间的因果关系，并重新排列它们以与这些因果关系对齐。这种重新排列可以建模为一个线性排列问题。由于每列对因果关系的贡献不同，我们进一步提出了一种重新加权策略，以给不同的列分配不同的权重以增强这种效果。在超过30个数据集上的实验表明，我们的方法在一致地优于当前最先进的方法。CausalTAD的代码可在https://github.com/350234/CausalTAD上获得。
英文摘要：
Detecting anomalies in tabular data is critical for many real-world applications, such as credit card fraud detection. With the rapid advancements in large language models (LLMs), state-of-the-art performance in tabular anomaly detection has been achieved by converting tabular data into text and fine-tuning LLMs. However, these methods randomly order columns during conversion, without considering the causal relationships between them, which is crucial for accurately detecting anomalies. In this paper, we present CausalTaD, a method that injects causal knowledge into LLMs for tabular anomaly detection. We first identify the causal relationships between columns and reorder them to align with these causal relationships. This reordering can be modeled as a linear ordering problem. Since each column contributes differently to the causal relationships, we further propose a reweighting strategy to assign different weights to different columns to enhance this effect. Experiments across more than 30 datasets demonstrate that our method consistently outperforms the current state-of-the-art methods. The code for CausalTAD is available at https://github.com/350234/CausalTAD.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
