RecGPT: Generative Pre-training for Text-based Recommendation

TL;DR

RecGPT-7B is a large, domain-adapted language model designed specifically for text-based recommendation tasks, demonstrating superior performance in rating prediction and sequential recommendation.

Contribution

This paper introduces RecGPT-7B and RecGPT-7B-Instruct, the first fully-trained large language models tailored for recommendation, with released datasets to support future research.

Findings

RecGPT-7B-Instruct outperforms previous baselines in recommendation tasks.

Models and datasets are publicly available for research use.

The approach advances text-based recommendation capabilities.

Abstract

We present the first domain-adapted and fully-trained large language model, RecGPT-7B, and its instruction-following variant, RecGPT-7B-Instruct, for text-based recommendation. Experimental results on rating prediction and sequential recommendation tasks show that our model, RecGPT-7B-Instruct, outperforms previous strong baselines. We are releasing our RecGPT models as well as their pre-training and fine-tuning datasets to facilitate future research and downstream applications in text-based recommendation. Public "huggingface" links to our RecGPT models and datasets are available at: https://github.com/VinAIResearch/RecGPT