RecGPT: Generative Pre-training for Text-based Recommendation

Hoang Ngo, Dat Quoc Nguyen
5/21/2024
cs.IRcs.CL

Official code: VinAIResearch/RecGPT (42 stars, last commit 2024-09-22).

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

View on arXivView PDF

Code Implementations(1)

VinAIResearch/RecGPTOfficial100%

RecGPT: Generative Pre-training for Text-based Recommendation (ACL 2024)

421PythonMay 21, 20242 years agoNOASSERTION
generative-pretraininggptlarge-language-modelllmrating-prediction+3 more

Similar Papers

RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm

86% match2024

Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning

84% match1 repo1412025

IDGenRec: LLM-RecSys Alignment with Textual ID Learning

83% match1 repo612024

RecGPT Technical Report

82% match2025

Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training

82% match2025

GenRec: Large Language Model for Generative Recommendation

81% match1 repo822023

Cite this paper

@article{ngo2024recgpt,
  title  = {RecGPT: Generative Pre-training for Text-based Recommendation},
  author = {Hoang Ngo and Dat Quoc Nguyen},
  year   = {2024},
  eprint = {2405.12715},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.12715v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.12715.svg)](https://codeofpaper.com/paper/2405.12715)

Discussion