跳到正文
arXiv cs.CL· Hoang Tran Vuong, Linh Ngo Van, Dang Nguyen, Thin Nguyen, Phuoc Nguyen, Mehrtash Harandi, Trung Le·· 2 天前AI 评分29

DiSPaT:基于 f-Divergence 自博弈微调的 LLM 表格异常检测框架

f-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models

AI 导读

研究者提出 DiSPaT,一个基于 f-divergence 最小化的自博弈微调框架,用于提升大语言模型对表格数据中正常样本分布的刻画能力。该方法通过交替优化:当前策略生成合成样本作为伪异常,critic 判别器学习区分其与真实正常样本,该信号驱动策略更新逐步对齐真实正常数据分布。

正文 · 原文

View PDF HTML (experimental)

Abstract:Anomaly detection in tabular data poses significant challenges due to heterogeneous feature types-mixing numerical, categorical, and textual attributes, which complicate learning meaningful representations of normality. Recent work has applied large language models (LLMs) to this problem by serializing table rows as text sequences, yet these approaches rely on one-shot supervised fine-tuning that offers limited signal to tighten the model's description of normality. We propose DiSPaT, a self-play fine-tuning framework that strengthens the model's understanding of normal data. Building on the theoretical foundation of f-divergence minimization, we derive a tight approximation connecting our training objective to reducing the distributional gap between real normal data and model-generated samples. DiSPaT operates through an alternating optimization: at each iteration, the current policy generates synthetic samples that serve as pseudo-anomalies, while a critic discriminator learns to distinguish these from real normal samples; this signal drives policy updates that progressively align the model distribution with the true normal-data distribution. Extensive experiments on diverse benchmarks demonstrate that DiSPaT consistently outperforms prior LLM-based methods, deep learning approaches, and classical unsupervised detectors for tabular anomaly detection.
Comments: Accepted at ICML 2026. 28 pages, 7 figures
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL)
Cite as: arXiv:2611.18370 [cs.LG]
  (or arXiv:2611.18370v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.18370

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hoang Tran [view email]
[v1] Fri, 13 Nov 2026 16:16:03 UTC (102 KB)

来源:arXiv cs.CL · arxiv.org