Saved in:
Bibliographic Details
Main Authors: Zhang, Xiaokun, He, Bowei, Chen, Jiamin, Cui, Ziqiang, Ma, Chen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19693
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908961060421632
author Zhang, Xiaokun
He, Bowei
Chen, Jiamin
Cui, Ziqiang
Ma, Chen
author_facet Zhang, Xiaokun
He, Bowei
Chen, Jiamin
Cui, Ziqiang
Ma, Chen
contents Large Language Models (LLMs) have recently gained increasing attention in the field of recommendation. Existing LLM-based methods typically represent items as token sequences, and apply attention layers on these tokens to generate recommendations. However, by inheriting the standard attention mechanism, these methods focus on modeling token-level relations. This token-centric focus overlooks the item as the fundamental unit of recommendation, preventing existing methods from effectively capturing collaborative relations at the item level. In this work, we revisit the role of tokens in LLM-driven recommendation and categorize their relations into two types: (1) intra-item token relations, which present the content semantics of an item, e.g., name, color, and size; and (2) inter-item token relations, which encode collaborative relations across items. Building on these insights, we propose a novel framework with an item-aware attention mechanism (IAM) to enhance LLMs for recommendation. Specifically, IAM devises two complementary attention layers: (1) an intra-item attention layer, which restricts attention to tokens within the same item, modeling item content semantics; and (2) an inter-item attention layer, which attends exclusively to token relations across items, capturing item collaborative relations. Through this stacked design, IAM explicitly emphasizes items as the fundamental units in recommendation, enabling LLMs to effectively exploit item-level collaborative relations. Extensive experiments on several public datasets demonstrate the effectiveness of IAM in enhancing LLMs for personalized recommendation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19693
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyong Tokens: Item-aware Attention for LLM-based Recommendation
Zhang, Xiaokun
He, Bowei
Chen, Jiamin
Cui, Ziqiang
Ma, Chen
Information Retrieval
Large Language Models (LLMs) have recently gained increasing attention in the field of recommendation. Existing LLM-based methods typically represent items as token sequences, and apply attention layers on these tokens to generate recommendations. However, by inheriting the standard attention mechanism, these methods focus on modeling token-level relations. This token-centric focus overlooks the item as the fundamental unit of recommendation, preventing existing methods from effectively capturing collaborative relations at the item level. In this work, we revisit the role of tokens in LLM-driven recommendation and categorize their relations into two types: (1) intra-item token relations, which present the content semantics of an item, e.g., name, color, and size; and (2) inter-item token relations, which encode collaborative relations across items. Building on these insights, we propose a novel framework with an item-aware attention mechanism (IAM) to enhance LLMs for recommendation. Specifically, IAM devises two complementary attention layers: (1) an intra-item attention layer, which restricts attention to tokens within the same item, modeling item content semantics; and (2) an inter-item attention layer, which attends exclusively to token relations across items, capturing item collaborative relations. Through this stacked design, IAM explicitly emphasizes items as the fundamental units in recommendation, enabling LLMs to effectively exploit item-level collaborative relations. Extensive experiments on several public datasets demonstrate the effectiveness of IAM in enhancing LLMs for personalized recommendation.
title Beyong Tokens: Item-aware Attention for LLM-based Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2603.19693