将推荐系统的隐向量映射为大模型可理解的文本标签，提升可解释性与效果。
FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens
- 分解协同过滤嵌入为概念向量，再转为大模型可用的词汇标记。
- 在三个真实数据集上提升基准模型性能，且生成的标签具备可解释性。
- 无需微调大模型，适用于各类推荐系统，适合关注可解释推荐的研究者。
近年来，大语言模型（LLMs）被探索用于与基于协同过滤（CF）的推荐系统融合，以实现个性化体验。然而，关键挑战在于LLMs难以理解CF生成的隐式、非语义嵌入，限制了推荐效果和后续应用。为此，我们提出FACE——一个通用的可解释框架，将CF嵌入映射为预训练LLM的词汇标记。具体地，引入解耦投影模块，将CF嵌入分解为概念特异性向量，并通过量化自编码器将连续嵌入转换为LLM词汇（描述符）。同时设计对比对齐目标，确保词汇与对应文本信号对齐。该模型无关的框架无需微调LLM即可实现语义对齐，并利用其预训练能力提升推荐性能。在三个真实世界推荐数据集上的实证结果表明，基准模型性能得到提升，可解释性研究证实描述符具有可解释性。代码已开源：https://github.com/YixinRoll/FACE。
原文摘要 · Abstract (English)
Recently, large language models (LLMs) have been explored for integration with collaborative filtering (CF)-based recommendation systems, which are crucial for personalizing user experiences. However, a key challenge is that LLMs struggle to interpret the latent, non-semantic embeddings produced by CF approaches, limiting recommendation effectiveness and further applications. To address this, we propose FACE, a general interpretable framework that maps CF embeddings into pre-trained LLM tokens. Specifically, we introduce a disentangled projection module to decompose CF embeddings into concept-specific vectors, followed by a quantized autoencoder to convert continuous embeddings into LLM tokens (descriptors). Then, we design a contrastive alignment objective to ensure that the tokens align with corresponding textual signals. Hence, the model-agnostic FACE framework achieves semantic alignment without fine-tuning LLMs and enhances recommendation performance by leveraging their pre-trained capabilities. Empirical results on three real-world recommendation datasets demonstrate performance improvements in benchmark models, with interpretability studies confirming the interpretability of the descriptors. Code is available in https://github.com/YixinRoll/FACE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。