# Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation Source: [Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation]() Collection index: [llms.txt]() Data updated: 2026-04-08T05:00:04.658Z Authors: Zhifu Wei, Yizhou Dang, Guibing Guo, Chuang Zhao, Zhu Sun Published: 2026-04-04T11:19:08.000Z ## Abstract Sequential Recommendation (SR) learns user preferences from their historical interaction sequences and provides personalized suggestions. In real-world scenarios, most items exhibit sparse interactions, known as the tail-item problem. This issue limits the model's ability to accurately capture item transition patterns. To tackle this, large language models (LLMs) offer a promising solution by capturing semantic relationships between items. Despite previous efforts to leverage LLM-derived embeddings for enriching tail items, they still face the following limitations: 1) They struggle to effectively fuse collaborative signals with semantic knowledge, leading to suboptimal item embedding quality. 2) Existing methods overlook the structural inconsistency between the ID and LLM embedding spaces, causing conflicting signals that degrade recommendation accuracy. In this work, we propose a Fusion and Alignment Enhancement framework with LLMs for Tail-item Sequential Recommendation (FAERec), which improves item representations by generating coherently-fused and structurally consistent embeddings. For the information fusion challenge, we design an adaptive gating mechanism that dynamically fuses ID and LLM embeddings. Then, we propose a dual-level alignment approach to mitigate structural inconsistency. The item-level alignment establishes correspondences between ID and LLM embeddings of the same item through contrastive learning, while the feature-level alignment constrains the correlation patterns between corresponding dimensions across the two embedding spaces. Furthermore, the weights of the two alignments are adjusted by a curriculum learning scheduler to avoid premature optimization of the complex feature-level objective. Extensive experiments across three widely used datasets with multiple representative SR backbones demonstrate the effectiveness and generalizability of our framework. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Sequential Recommendation on Beauty (H@10, N@10)](): Sequential Recommendation; Beauty Overall; H@10: 6.44. - [Sequential Recommendation on Beauty Tail](): Sequential Recommendation; Beauty Tail; Hit Rate@10: 0.0645. - [Sequential Recommendation on Grocery Overall](): Sequential Recommendation; Grocery Overall; Hit Rate@10: 7.76. - [Sequential Recommendation on Grocery Tail](): Sequential Recommendation; Grocery Tail; Hit Rate @10: 7.37. - [Sequential Recommendation on Beauty (Cov@10, TCov@10)](): Sequential Recommendation; Beauty; Coverage@10: 86.12. - [Sequential Recommendation on Yelp (Overall)](): Sequential Recommendation; Yelp (Overall); Hit Rate @10: 0.0461. - [Sequential Recommendation on Yelp (Tail)](): Sequential Recommendation; Yelp (Tail); Hit Rate@10: 0.97. ## Original sources and implementation [Original paper]() [PDF]()