Relationship Detection on Tabular Data Using Statistical Analysis and Large Language Models

TL;DR

This paper presents a hybrid method combining statistical analysis and large language models to detect relationships among columns in unlabeled tabular data, leveraging Knowledge Graphs and benchmarking against state-of-the-art approaches.

Contribution

It introduces a novel hybrid approach that reduces the search space for relationship detection using statistical constraints and LLMs, evaluated on benchmark datasets.

Findings

The method is competitive with state-of-the-art approaches.

Statistical modules improve LLM-based relationship detection.

Different prompting techniques affect LLM performance.

Abstract

Over the past few years, table interpretation tasks have made significant progress due to their importance and the introduction of new technologies and benchmarks in the field. This work experiments with a hybrid approach for detecting relationships among columns of unlabeled tabular data, using a Knowledge Graph (KG) as a reference point, a task known as CPA. This approach leverages large language models (LLMs) while employing statistical analysis to reduce the search space of potential KG relations. The main modules of this approach for reducing the search space are domain and range constraints detection, as well as relation co-appearance analysis. The experimental evaluation on two benchmark datasets provided by the SemTab challenge assesses the influence of each module and the effectiveness of different state-of-the-art LLMs at various levels of quantization. The experiments were performed, as well as at different prompting techniques. The proposed methodology, which is publicly available on github, proved to be competitive with state-of-the-art approaches on these datasets.