用因果关系重排表格列，提升大模型异常检测效果
CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection
- 根据列间因果关系重新排序表格数据，优化输入结构
- 在30+数据集上超越现有最优方法，平均性能提升显著
- 适合需要高精度异常检测的金融、风控等场景
表格式数据中的异常检测在信用卡欺诈等实际应用中至关重要。随着大语言模型（LLMs）的发展，通过将表格数据转换为文本并微调LLM，已实现表格式异常检测的先进性能。然而，现有方法在转换时随机排列列顺序，未考虑列之间的因果关系，而因果关系对准确识别异常至关重要。本文提出CausalTAD，一种将因果知识注入大语言模型以实现表格式异常检测的方法。首先，我们识别列间的因果关系，并据此重新排序列，该过程可建模为线性排序问题。由于各列在因果关系中作用不同，我们进一步提出重加权策略，为不同列分配不同权重以增强效果。在超过30个数据集上的实验表明，本方法持续优于当前最先进的方法。CausalTAD代码已开源：https://github.com/350234/CausalTAD。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。