大型語言模型在語言和基於項目的偏好的冷啟動推薦系統中具有競爭力。

摘要

傳統的推薦系統利用使用者的物品偏好歷史來推薦使用者可能喜歡的新內容。然而，現代對話界面允許使用者表達基於語言的偏好，提供了一種根本不同的偏好輸入模式。受到大型語言模型（LLMs）提示範式在最近取得的成功的啟發，我們研究了它們在基於物品和基於語言偏好下進行推薦的應用，並與最先進的基於物品的協同過濾（CF）方法進行比較。為了支持這一研究，我們收集了一個新的數據集，其中包含從使用者那裡獲得的基於物品和基於語言的偏好，以及他們對各種（有偏見的）推薦物品和（無偏見的）隨機物品的評分。在眾多的實驗結果中，我們發現LLMs在純粹基於語言偏好（無物品偏好）的情況下，在接近冷啟動情況下相對於基於物品的CF方法提供了有競爭力的推薦性能，儘管對於這特定任務沒有監督訓練（零-shot）或僅有少量標籤（少-shot）。這尤其令人鼓舞，因為基於語言偏好的表示比基於物品或向量表示更具可解釋性和可檢視性。

English

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.

大型語言模型在語言和基於項目的偏好的冷啟動推薦系統中具有競爭力。

Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences

摘要

Support