Large Language Model-based Recommender Systems (LRSs) have recently emerged as a new paradigm in sequential recommendation by directly adopting LLMs as backbones. While LRSs demonstrate strong knowledge utilization and instruction-following abilities, they have not been systematically studied under the long-standing long-tail problem. In this paper, we conduct an empirical study and reveal that LRSs face two distinct types of long-tail: i) prior long-tail, inherited implicitly from pretraining corpora, and ii) data long-tail, originating from skewed recommendation datasets. Our analysis shows that both contribute to the performance disparity between head and tail items, with the intersection of the two heads exhibiting an even stronger head effect. Nevertheless, the overall performance distribution in LRSs, especially on the tail, remains dominated by the data long-tail. To address this challenge, we propose Efficient Item-wise Sharpness-Aware Minimization (EISAM), a novel optimization framework that improves tail-item performance by adaptively regularizing the loss landscape at the item level. EISAM introduces an efficient penalty design that captures fine-grained item-specific sharpness while maintaining computational scalability for LLMs. In addition, we derive a generalization bound for EISAM. Our theoretical analysis shows that the bound decreases at a faster rate under our item-wise regularization, offering theoretical support for its effectiveness. Extensive experiments on three real-world datasets demonstrate that EISAM significantly boosts tail-item recommendation performance while preserving overall quality, establishing the first systematic solution to the long-tail problem in LRSs.

翻译：基于大型语言模型的推荐系统（LRSs）作为一种新范式，通过直接采用LLM作为骨干网络，已在序列推荐领域崭露头角。尽管LRSs展现出强大的知识利用与指令遵循能力，其在长期存在的长尾问题下的表现尚未得到系统研究。本文通过实证研究发现，LRSs面临两种不同类型的长尾：i) 先验长尾，即从预训练语料中隐式继承的分布偏斜；ii) 数据长尾，源于推荐数据集本身的分布不均衡。分析表明，两者均导致头部与尾部物品间的性能差异，且当两种长尾效应叠加时，头部效应会进一步增强。然而，LRSs的整体性能分布（尤其在尾部）仍主要受数据长尾主导。为应对这一挑战，我们提出高效逐项锐度感知最小化（EISAM），一种新颖的优化框架，通过在物品层级自适应正则化损失函数的几何形态来提升尾部物品性能。EISAM设计了高效的正则项，能够捕捉细粒度的物品特异性锐度，同时保持对LLM计算的可扩展性。此外，我们推导了EISAM的泛化误差上界。理论分析表明，在逐项正则化下该上界以更快的速率下降，为其有效性提供了理论支撑。在三个真实数据集上的大量实验表明，EISAM在保持整体推荐质量的同时，显著提升了尾部物品的推荐性能，为LRSs中的长尾问题提供了首个系统性解决方案。