Anomaly Detection of Tabular Data Using LLMs
This addresses the challenge of anomaly detection in tabular data for data analysis and security applications, presenting an incremental approach by adapting existing LLMs to this task.
The paper tackles the problem of detecting anomalies in tabular data using large language models (LLMs), showing that pre-trained LLMs can perform zero-shot batch-level anomaly detection and that fine-tuning with synthetic datasets improves their performance to match state-of-the-art methods on the ODDS benchmark.
Large language models (LLMs) have shown their potential in long-context understanding and mathematical reasoning. In this paper, we study the problem of using LLMs to detect tabular anomalies and show that pre-trained LLMs are zero-shot batch-level anomaly detectors. That is, without extra distribution-specific model fitting, they can discover hidden outliers in a batch of data, demonstrating their ability to identify low-density data regions. For LLMs that are not well aligned with anomaly detection and frequently output factual errors, we apply simple yet effective data-generating processes to simulate synthetic batch-level anomaly detection datasets and propose an end-to-end fine-tuning strategy to bring out the potential of LLMs in detecting real anomalies. Experiments on a large anomaly detection benchmark (ODDS) showcase i) GPT-4 has on-par performance with the state-of-the-art transductive learning-based anomaly detection methods and ii) the efficacy of our synthetic dataset and fine-tuning strategy in aligning LLMs to this task.