Traditional recommender systems leverage users' item preference history to recommend novel content that users may like. However, modern dialog interfaces that allow users to express language-based preferences offer a fundamentally different modality for preference input. Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods. To support this investigation, we collect a new dataset consisting of both item-based and language-based preferences elicited from users along with their ratings on a variety of (biased) recommended items and (unbiased) random items. Among numerous experimental results, we find that LLMs provide competitive recommendation performance for pure language-based preferences (no item preferences) in the near cold-start case in comparison to item-based CF methods, despite having no supervised training for this specific task (zero-shot) or only a few labels (few-shot). This is particularly promising as language-based preference representations are more explainable and scrutable than item-based or vector-based representations.

翻译：传统推荐系统利用用户的物品偏好历史，推荐用户可能喜欢的新内容。然而，允许用户表达基于语言偏好的现代对话界面，为偏好输入提供了一种根本不同的方式。受大型语言模型（LLM）提示范式近期成功的启发，我们研究了如何利用它们从基于物品和基于语言的偏好中进行推荐，并与最先进的基于物品的协同过滤（CF）方法进行比较。为支持这一研究，我们收集了一个新数据集，其中包含用户提供的基于物品和基于语言的偏好，以及他们对各种（有偏见的）推荐物品和（无偏见的）随机物品的评分。在众多实验结果中，我们发现，在近冷启动情况下，LLM在仅基于语言偏好（无物品偏好）的推荐性能上与基于物品的CF方法相当，尽管它们没有针对此特定任务进行监督训练（零样本）或仅使用少量标签（少样本）。这一发现尤其令人鼓舞，因为基于语言的偏好表示比基于物品或基于向量的表示更具可解释性和可审阅性。