重新思考大语言模型增强型协同过滤中的语义对齐：一种谱解耦方法
Rethinking Semantic Alignment in LLM-Enhanced Collaborative Filtering: A Spectral Decoupling Approach
AI总结：
本研究针对LLM增强型推荐中语义对齐无法有效利用互补非主语义信息的问题，提出UniSpecRec模型，通过信号特异性谱滤波实现谱解耦，提升推荐性能。
AI中文摘要：
近期大语言模型（LLM）增强型推荐的进展通常会将语义表示与协同嵌入在共享空间中对齐，但这种对齐如何影响LLM编码的信息仍不清楚。在本研究中，我们从谱视角重新审视LLM增强型推荐，发现协同信号和语义信号受益于不同的谱部分：协同表示因用户-物品同质性而由平滑的低频分量主导，而语义嵌入则包含有用的非主奇异分量。通过逐分量评估和训练动态分析，我们发现对齐会使学习到的表示逐渐集中在主导协同子空间和主语义子空间中，从而减少与非主语义分量的重叠。对照实验表明，非主分量在对齐下提供的增益不稳定，但通过分量级解耦可持续提升性能，而完整预测级解耦则实现了最佳整体性能。这些结果表明，对齐无法有效利用互补的非主语义信息。基于这些发现，我们提出UniSpecRec（用于推荐的统一谱信号模型），该模型应用信号特异性谱滤波，同时将协同表示和语义表示保留在各自的空间中，无需跨空间对齐或额外可训练参数，仅结合两者的预测即可。大量实验证明了该模型的有效性、效率和可泛化性。
英文摘要：
Recent advances in LLM-enhanced recommendation commonly align semantic representations with collaborative embeddings in a shared space, yet how alignment affects LLM-encoded information remains unclear. In this work, we revisit LLM-enhanced recommendation from a spectral perspective and show that collaborative and semantic signals benefit from different spectral parts. While collaborative representations are dominated by smooth low-frequency components due to user-item homophily, semantic embeddings contain useful non-principal singular components. Through component-wise evaluation and training-dynamics analysis, we find that alignment increasingly concentrates learned representations in dominant collaborative and principal semantic subspaces, reducing overlap with non-principal semantic components. Controlled comparisons show that non-principal components provide inconsistent gains under alignment but consistently improve performance through component-level decoupling, while full prediction-level decoupling achieves the best overall performance. These results indicate that alignment fails to effectively exploit complementary non-principal semantic information. Motivated by these findings, we propose UniSpecRec (Unifying Spectral Signals for Recommendation), which applies signal-specific spectral filtering while preserving collaborative and semantic representations in their respective spaces. UniSpecRec combines their predictions without cross-space alignment or additional trainable parameters. Extensive experiments demonstrate its effectiveness, efficiency, and generalizability.
