# rLLM: Relational Table Learning with LLMs

Source: [rLLM: Relational Table Learning with LLMs](<https://www.sota2.com/research/paper/68fa74511e209131cea61031>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T06:57:41.621Z

Authors: Weichen Li, Xiaotong Huang, Jianwu Zheng, Zheng Wang, Chaokun Wang, Li Pan, Jianhua Li

Published: 2024-07-29T16:33:40.000Z

## Abstract

We introduce rLLM (relationLLM), a PyTorch library designed for Relational Table Learning (RTL) with Large Language Models (LLMs). The core idea is to decompose state-of-the-art Graph Neural Networks, LLMs, and Table Neural Networks into standardized modules, to enable the fast construction of novel RTL-type models in a simple "combine, align, and co-train" manner. To illustrate the usage of rLLM, we introduce a simple RTL method named \\textbf{BRIDGE}. Additionally, we present three novel relational tabular datasets (TML1M, TLF2K, and TACM12K) by enhancing classic datasets. We hope rLLM can serve as a useful and easy-to-use development framework for RTL-related tasks. Our code is available at: https://github.com/rllm-project/rllm.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Classification on TML1M v1 (test)](<https://www.sota2.com/research/sota/classification-on-tml1m-v1-test.md>): Classification; TML1M v1 (test); Accuracy: 36.2.

- [Classification on TLF2K v1 (test)](<https://www.sota2.com/research/sota/classification-on-tlf2k-v1-test.md>): Classification; TLF2K v1 (test); Accuracy: 42.2.

- [Classification on TACM12K v1 (test)](<https://www.sota2.com/research/sota/classification-on-tacm12k-v1-test.md>): Classification; TACM12K v1 (test); Accuracy: 25.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.20157>)

[PDF](<https://arxiv.org/pdf/2407.20157.pdf>)

[Implementation](<https://github.com/rllm-project/rllm>)
