# CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection

arXiv: https://arxiv.org/abs/2602.07798 · HTML: https://mlsanity.com/paper/2602.07798/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions](https://mlsanity.com/paper/2201.00382/) (2022)
- [VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2308.11681/) (2023)
- [DROCC: Deep Robust One-Class Classification](https://mlsanity.com/paper/2002.12718/) (2020)
- [Neural Transformation Learning for Deep Anomaly Detection Beyond Images](https://mlsanity.com/paper/2103.16440/) (2021)
- [Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection](https://mlsanity.com/paper/1806.04808/) (2018)
- [On Diffusion Modeling for Anomaly Detection](https://mlsanity.com/paper/2305.18593/) (2023)
- [Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2407.10299/) (2024)
- [Representation Learning for Tabular Data: A Comprehensive Survey](https://mlsanity.com/paper/2504.16109/) (2025)
- [Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning](https://mlsanity.com/paper/2305.16114/) (2023)
- [TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields](https://mlsanity.com/paper/2505.18125/) (2025)
- [Anomaly Detection of Tabular Data Using LLMs](https://mlsanity.com/paper/2406.16308/) (2024)
- [Deep Causal Learning: Representation, Discovery and Inference](https://mlsanity.com/paper/2211.03374/) (2022)
- [When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series](https://mlsanity.com/paper/2506.23596/) (2025)
- [Retrieval Augmented Deep Anomaly Detection for Tabular Data](https://mlsanity.com/paper/2401.17052/) (2024)
- [Unsupervised Anomaly Detection for Tabular Data Using Noise Evaluation](https://mlsanity.com/paper/2412.11461/) (2024)
- [Adapting Large Language Models for Parameter-Efficient Log Anomaly Detection](https://mlsanity.com/paper/2503.08045/) (2025)
- [ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection](https://mlsanity.com/paper/2510.02060/) (2025)

## Built on by (most cited first, 1 of 1)

- [Traceable LLM Reasoning for Fake-Order Fraud Detection](https://mlsanity.com/paper/2607.23075/) (2026)

## Abstract (arXiv)

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.