RecAI: Leveraging Large Language Models for Next-Generation Recommender Systems

Jianxun Lian, Yuxuan Lei, Xu Huang, Jing Yao, Wei Xu +1 more
3/11/2024
cs.IRcs.AI

Official code: microsoft/RecAI (1,179 stars, MIT, last commit 2026-01-27).

Abstract

This paper introduces RecAI, a practical toolkit designed to augment or even revolutionize recommender systems with the advanced capabilities of Large Language Models (LLMs). RecAI provides a suite of tools, including Recommender AI Agent, Recommendation-oriented Language Models, Knowledge Plugin, RecExplainer, and Evaluator, to facilitate the integration of LLMs into recommender systems from multifaceted perspectives. The new generation of recommender systems, empowered by LLMs, are expected to be more versatile, explainable, conversational, and controllable, paving the way for more intelligent and user-centric recommendation experiences. We hope the open-source of RecAI can help accelerate evolution of new advanced recommender systems. The source code of RecAI is available at \url{https://github.com/microsoft/RecAI}.

View on arXivView PDF

Code Implementations(1)

microsoft/RecAIOfficial100%
MIT

Bridging LLM and Recommender System.

1,179123Shell, PythonSep 7, 20238 months agoMIT
llmrecommender

Similar Papers

Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review

87% match2024

Navigating User Experience of ChatGPT-based Conversational Recommender Systems: The Effects of Prompt Guidance and Recommendation Domain

86% match2024

OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation

85% match2024

Enhancing ID-based Recommendation with Large Language Models

84% match1 repo82024

Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models

84% match2025

LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application

83% match1 repo302024

Cite this paper

@article{lian2024recai,
  title  = {RecAI: Leveraging Large Language Models for Next-Generation Recommender Systems},
  author = {Jianxun Lian and Yuxuan Lei and Xu Huang and Jing Yao and Wei Xu and Xing Xie},
  year   = {2024},
  eprint = {2403.06465},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.06465v1}
}

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/2403.06465.svg)](https://codeofpaper.com/paper/2403.06465)

Discussion