用大模型解析多维度数据中的隐藏模式，无需依赖标签或辅助数据。
AnTenA: Actionable and Explainable Tensor Analysis System with Large Language Models
- 通过张量分解提取潜在共聚类模式，结合任务相关与无关提示生成解释。
- 在正向与反向推理任务中验证解释效果，证明方法有效性。
- 适合缺乏标注数据的场景，如动态时间序列分析与叙事数据挖掘。
准确解释多维度数据中的隐藏模式通常依赖标签或辅助元数据。然而，这些数据可能不准确（如非标准、不一致）、不足（如静态表格数据无法反映时变记录）或完全缺失。本文提出 ullmethod ( extit{AnTenA})，利用大语言模型（LLMs）的知识来解释人类叙事中的隐藏模式。该方法通过任务无关和任务相关的提示，对张量分解提取的共聚类潜在模式进行解释。为评估解释质量，我们在正向与反向推理任务上测试了LLM的表现。演示系统已开源，地址为 https://github.com/dawonahn/ECML_PKDD_AnTenA。
原文摘要 · Abstract (English)
Accurately explaining hidden patterns in multi-aspect data has typically been done by leveraging labels and/or accompanying auxiliary metadata. However, labels and auxiliary data may be inaccurate (e.g. nonstandard, inconsistent), insufficient (e.g. static tabular metadata for time-dependent recordings), or unavailable. % We propose \fullmethod (\method), which leverages the knowledge of large language models (LLMs) to explain the hidden patterns in human narratives. \method uses task-agnostic and task-specific prompts to explain extracted co-clustered latent patterns from tensor decomposition. To evaluate these explanations, we test the LLMs on forward and backward inference tasks. % Our demo system is available at https://github.com/dawonahn/ECML_PKDD_AnTenA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。