让协同信号发挥作用：面向序列推荐的图感知大语言模型
Making Collaborative Signals Count: Graph-Aware Large Language Models for Sequential Recommendation
浏览论文内容
中文总结 AI 辅助
针对现有序列推荐方法难以捕捉全局协同模式的问题，提出图感知大语言模型框架GALLM，通过构建协同图建模三类关系并整合至注意力机制，在四个基准上取得最优性能，HR@5较最强基线平均提升9.76%。
中文摘要 AI 辅助
大语言模型（LLMs）已被广泛用作推荐系统的骨干，但它们以语言为中心的预训练使其难以捕捉用户-物品交互中隐含的协同信号，而协同信号对个性化推荐至关重要。现有方法要么注入外部推荐器生成的协同表示，要么仅建模序列内依赖关系，限制了其利用全局协同模式的能力。为解决这一局限，我们提出GALLM，一种面向序列推荐的图感知大语言模型框架。GALLM在文本令牌和物品令牌上构建协同图，并建模三类关系：文本-文本关系以保留语义依赖、物品-文本关系以对齐物品令牌与其文本描述、物品-物品关系则源自全局物品共现模式。这些关系被转换为轻量级可学习注意力偏置，并整合到大语言模型的注意力机制中，从而在不引入额外图编码器的情况下实现感知协同的令牌交互。在四个真实世界基准上的实验表明，GALLM在对比基线中取得最佳性能，在HR@5指标上较最强基线平均提升9.76%。
英文摘要
Large language models (LLMs) have been widely adopted as backbones for recommender systems. However, their language-centric pretraining makes it difficult to capture collaborative signals implicit in user-item interactions, which are crucial for personalized recommendation. Existing methods either inject collaborative representations produced by external recommenders or model only intra-sequence dependencies, limiting their ability to exploit global collaborative patterns. To address this limitation, we propose GALLM, a graph-aware LLM framework for sequential recommendation. GALLM constructs a collaborative graph over text tokens and item tokens, and models three types of relations: Text--Text relations for preserving semantic dependencies, Item--Text relations for aligning item tokens with their textual descriptions, and Item--Item relations derived from global item co-occurrence patterns. These relations are transformed into lightweight learnable attention biases and incorporated into the LLM attention mechanism, enabling collaborative-aware token interactions without introducing an additional graph encoder. Experiments on four real-world benchmarks show that GALLM achieves the best performance among the compared baselines, improving over the strongest baseline by 9.76\% on average in HR@5.
