Recommender systems are widely used in various online services, with embedding-based models being particularly popular due to their expressiveness in representing complex signals. However, these models often lack interpretability, making them less reliable and transparent for both users and developers. With the emergence of large language models (LLMs), we find that their capabilities in language expression, knowledge-aware reasoning, and instruction following are exceptionally powerful. Based on this, we propose a new model interpretation approach for recommender systems, by using LLMs as surrogate models and learn to mimic and comprehend target recommender models. Specifically, we introduce three alignment methods: behavior alignment, intention alignment, and hybrid alignment. Behavior alignment operates in the language space, representing user preferences and item information as text to learn the recommendation model's behavior; intention alignment works in the latent space of the recommendation model, using user and item representations to understand the model's behavior; hybrid alignment combines both language and latent spaces for alignment training. To demonstrate the effectiveness of our methods, we conduct evaluation from two perspectives: alignment effect, and explanation generation ability on three public datasets. Experimental results indicate that our approach effectively enables LLMs to comprehend the patterns of recommendation models and generate highly credible recommendation explanations.

翻译：推荐系统广泛应用于各类在线服务中，其中基于嵌入的模型因其对复杂信号表达的强大能力而尤为流行。然而，这类模型通常缺乏可解释性，导致对用户和开发者而言可靠性与透明度不足。随着大型语言模型（LLM）的出现，我们发现其在语言表达、知识感知推理与指令遵循方面的能力异常强大。基于此，我们提出一种面向推荐系统的新型模型解释方法——利用LLM作为替代模型，通过学习来模拟和理解目标推荐模型。具体而言，我们引入了三种对齐方法：行为对齐、意图对齐与混合对齐。行为对齐在语言空间中运作，将用户偏好与物品信息表征为文本，以学习推荐模型的行为；意图对齐在推荐模型的隐空间中运作，利用用户和物品表示来理解模型行为；混合对齐则结合语言空间与隐空间进行对齐训练。为验证方法的有效性，我们从对齐效果与解释生成能力两个维度，在三个公开数据集上开展评估。实验结果表明，我们的方法能有效促使LLM理解推荐模型的模式，并生成可信度极高的推荐解释。