Recent studies empirically indicate that language models (LMs) encode rich world knowledge beyond mere semantics, attracting significant attention across various fields. However, in the recommendation domain, it remains uncertain whether LMs implicitly encode user preference information. Contrary to the prevailing understanding that LMs and traditional recommender models learn two distinct representation spaces due to a huge gap in language and behavior modeling objectives, this work rethinks such understanding and explores extracting a recommendation space directly from the language representation space. Surprisingly, our findings demonstrate that item representations, when linearly mapped from advanced LM representations, yield superior recommendation performance. This outcome suggests the homomorphism between the language representation space and an effective recommendation space, implying that collaborative signals may indeed be encoded within advanced LMs. Motivated by these findings, we propose a simple yet effective collaborative filtering (CF) model named AlphaRec, which utilizes language representations of item textual metadata (e.g., titles) instead of traditional ID-based embeddings. Specifically, AlphaRec is comprised of three main components: a multilayer perceptron (MLP), graph convolution, and contrastive learning (CL) loss function, making it extremely easy to implement and train. Our empirical results show that AlphaRec outperforms leading ID-based CF models on multiple datasets, marking the first instance of such a recommender with text embeddings achieving this level of performance. Moreover, AlphaRec introduces a new language-representation-based CF paradigm with several desirable advantages: being easy to implement, lightweight, rapid convergence, superior zero-shot recommendation abilities in new domains, and being aware of user intention.

翻译：近期研究经验表明，语言模型（LMs）编码了超越单纯语义的丰富世界知识，这引起了多个领域的广泛关注。然而，在推荐领域，语言模型是否隐式编码了用户偏好信息仍不明确。与普遍认为语言模型和传统推荐模型因语言建模目标与行为建模目标存在巨大差异而学习两个截然不同的表示空间的观点相反，本研究重新审视了这一理解，并探索直接从语言表示空间中提取推荐空间。令人惊讶的是，我们的研究结果表明，当从先进的语言模型表示中线性映射得到物品表示时，能够产生卓越的推荐性能。这一结果揭示了语言表示空间与有效推荐空间之间的同态性，暗示协同信号可能确实被编码在先进的语言模型中。受这些发现的启发，我们提出了一种简单而有效的协同过滤（CF）模型，命名为AlphaRec，该模型利用物品文本元数据（例如标题）的语言表示，而非传统的基于ID的嵌入。具体而言，AlphaRec由三个主要组件构成：一个多层感知机（MLP）、图卷积以及对比学习（CL）损失函数，这使得其实现和训练极为简便。我们的实证结果表明，AlphaRec在多个数据集上超越了领先的基于ID的协同过滤模型，标志着首个基于文本嵌入的推荐器达到如此性能水平。此外，AlphaRec引入了一种新的基于语言表示的协同过滤范式，具有多项理想优势：易于实现、轻量级、快速收敛、在新领域中具有卓越的零样本推荐能力，并能感知用户意图。