Enhancing High-order Interaction Awareness in LLM-based Recommender Model

Xinfeng Wang, Jin Cui, Fumiyo Fukumoto, Yoshimi Suzuki
9/30/2024
cs.IRcs.CL

No official code found. Best implementation: WangXFng/ELMRec (13 stars, last commit 2025-01-09).

Abstract

Large language models (LLMs) have demonstrated prominent reasoning capabilities in recommendation tasks by transforming them into text-generation tasks. However, existing approaches either disregard or ineffectively model the user-item high-order interactions. To this end, this paper presents an enhanced LLM-based recommender (ELMRec). We enhance whole-word embeddings to substantially enhance LLMs' interpretation of graph-constructed interactions for recommendations, without requiring graph pre-training. This finding may inspire endeavors to incorporate rich knowledge graphs into LLM-based recommenders via whole-word embedding. We also found that LLMs often recommend items based on users' earlier interactions rather than recent ones, and present a reranking solution. Our ELMRec outperforms state-of-the-art (SOTA) methods in both direct and sequential recommendations.

View on arXivView PDF

Code Implementations(1)

WangXFng/ELMRecCommunity100%

[EMNLP 2024] Enhancing High-order Interaction Awareness in LLM-based Recommender Model.

132PythonJun 14, 20241 years ago

Similar Papers

Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?

89% match2026

LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation

89% match2 repos522024

Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models

89% match2024

Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation

88% match2026

Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation

88% match2025

Large Language Models Make Sample-Efficient Recommender Systems

88% match2024

Cite this paper

@article{wang2024enhancing,
  title  = {Enhancing High-order Interaction Awareness in LLM-based Recommender Model},
  author = {Xinfeng Wang and Jin Cui and Fumiyo Fukumoto and Yoshimi Suzuki},
  year   = {2024},
  eprint = {2409.19979},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.19979v3}
}

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/2409.19979.svg)](https://codeofpaper.com/paper/2409.19979)

Discussion