WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web

TL;DR

WebRec introduces a web-based RAG framework that leverages LLM reasoning and an attention-enhancement mechanism to improve web retrieval for personalized recommendations, addressing noise and knowledge gaps.

Contribution

The paper presents WebRec, a novel framework that effectively integrates web retrieval with LLMs for recommendations, including a new MP-Head for handling noisy, scattered web information.

Findings

WebRec outperforms existing methods in recommendation accuracy.

The MP-Head improves attention to relevant web information.

WebRec effectively handles noisy and scattered web data.

Abstract

Recommender systems play a vital role in alleviating information overload and enriching users' online experience. In the era of large language models (LLMs), LLM-based recommender systems have emerged as a prevalent paradigm for advancing personalized recommendations. Recently, retrieval-augmented generation (RAG) has drawn growing interest to facilitate the recommendation capability of LLMs, incorporating useful information retrieved from external knowledge bases. However, as a rich source of up-to-date information, the web remains under-explored by existing RAG-based recommendations. In particular, unique challenges are posed from two perspectives: one is to generate effective queries for web retrieval, considering the inherent knowledge gap between web search and recommendations; another challenge lies in harnessing online websites that contain substantial noisy content. To tackle these limitations, we propose WebRec, a novel web-based RAG framework, which takes advantage of the reasoning capability of LLMs to interpret recommendation tasks into queries of user preferences that cater to web retrieval. Moreover, given noisy web-retrieved information, where relevant pieces of evidence are scattered far apart, an insightful MP-Head is designed to enhance LLM attentions between distant tokens of relevant information via message passing. Extensive experiments have been conducted to demonstrate the effectiveness of our proposed web-based RAG methods in recommendation scenarios.