AnTenA: Actionable and Explainable Tensor Analysis System with Large Language Models
Provides a novel method for explaining tensor decomposition patterns in data-scarce scenarios, but evaluation is limited to inference tasks without concrete performance numbers.
AnTenA uses LLMs to explain hidden patterns in multi-aspect data without relying on labels or metadata, demonstrating effectiveness through forward and backward inference tasks.
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.