Metraipolis › archive › dc_4ade18b388db
LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection — arXiv:2608.19463
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19463
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T11:48:06.865Z
- SHA-256 of the archived text
5918ea0f85bbccad1c23138ba57a2435e8e2ce2c1eada63dca13896a769edcad- Stable URL of this page
https://metraipolis.com/documento/dc_4ade18b388db
How to cite
LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection — arXiv:2608.19463 — arXiv (en), https://arxiv.org/abs/2608.19463 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4ade18b388db (Metraipolis archive dc_4ade18b388db, sha256 5918ea0f85bbccad1c23138ba57a2435e8e2ce2c1eada63dca13896a769edcad)
BibTeX
@misc{dc4ade18b388db,
title = {LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection — arXiv:2608.19463},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19463},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4ade18b388db; sha256 5918ea0f85bbccad1c23138ba57a2435e8e2ce2c1eada63dca13896a769edcad},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19463. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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-tune LLMs with normal samples or generate synthetic anomalies. We propose LLM-Detector, a framework that utilizes the in-context learning capacity of LLMs for structured, prompt-conditioned scoring synthesis, enabling LLMs to derive anomaly detection logic from structured normal-state knowledge. Specifically, normal training data are converted into statistical summaries, causal dependencies, and distilled prototypes that are organized into a prompt for code generation. The resulting scoring engine evaluates statistical deviation, structural inconsistency, and density-based abnormality then computes an anomaly score for each test sample. We evaluate LLM-Detector on 24 tabular datasets, comparing against 15 SOTA baselines. Results show consistent improvements across both mixed-type and continuous-only settings. Moreover, this design eliminates the need for LLM fine-tuning or neural network training, reducing computational cost and enabling practical anomaly detection in real-world tabular systems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.19463 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T11:47:43.297Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).