LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection
Leveraging in-context learning to identify complex structural anomalies in tabular data without model training.
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-t...
ArXiv CS.LG
Source
Generated insight by OnAirToday AI
This research demonstrates that LLMs can act as zero-shot reasoning engines for complex tabular data analysis by leveraging in-context learning instead of traditional fine-tuning. By converting data into causal dependencies and statistical prototypes, the framework offers a more interpretable and resource-efficient path to identifying structural anomalies.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.