AnTenA: Actionable and Explainable Tensor Analysis System with Large Language Models
Quick Answer
AnTenA is a novel system that utilizes large language models to explain hidden patterns in multi-aspect data without relying on potentially inaccurate labels or auxiliary metadata.
Quick Take
AnTenA is a novel system that utilizes large language models to explain hidden patterns in multi-aspect data without relying on potentially inaccurate labels or auxiliary metadata. It employs both task-agnostic and task-specific prompts to derive explanations from tensor decomposition, demonstrating its effectiveness through forward and backward inference tasks.
Key Points
- AnTenA leverages large language models for data pattern explanations.
- The system operates without relying on potentially inaccurate labels.
- It uses tensor decomposition to extract co-clustered latent patterns.
- Evaluation includes testing LLMs on forward and backward inference tasks.
- A demo system is available for public access.
Paper Resources
📖 Reader Mode
~1 min readAbstract: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 this https URL.
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.28708 [cs.CL] |
| (or arXiv:2606.28708v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.28708 arXiv-issued DOI via DataCite |
Submission history
From: Dawon Ahn [view email]
[v1]
Sat, 27 Jun 2026 03:29:49 UTC (550 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.