This repository curates research on applying Large Language Models (LLMs) to tabular data, a critical but often overlooked data format. It serves as a valuable resource for researchers and practitioners seeking to leverage LLMs for tasks like data generation, prediction, question answering, and understanding within tabular contexts, aiming to accelerate progress in this specialized area.

How It Works

This project is a curated list, not a software library. It compiles and categorizes academic papers, workshops, and blogs that explore the intersection of LLMs and tabular data. The core value lies in its comprehensive and up-to-date cataloging of research, providing a structured overview of the evolving landscape and key contributions in this domain.

Quick Start & Requirements

This is a curated list of research papers and does not involve direct installation or execution of code. The primary requirement is an interest in the field of LLMs applied to tabular data.

Highlighted Details

• Comprehensive list of over 40 research papers from 2019 to 2024, covering diverse applications.
• Includes related workshops and useful blogs for broader context.
• Papers cover key areas such as data generation, prediction, question answering, and representation learning.
• Actively maintained with recent publications and community contributions welcomed.

Maintenance & Community

The project is actively under development and welcomes community contributions to update the list with new research and correct any inaccuracies. The author's ORCID is provided for reference.

Licensing & Compatibility

The repository itself is licensed under an unspecified license, but it primarily links to external research papers, each with its own licensing and usage terms. Compatibility for commercial use or closed-source linking depends on the licenses of the individual papers referenced.

Limitations & Caveats

As a curated list, this repository does not provide code implementations or benchmarks. The "Resources" column in the paper table is often empty, requiring users to find external links for actual resources. The project is explicitly stated to be under development.