對話推薦的項目語言模型

Item-Language Model for Conversational Recommendation

June 5, 2024

作者: Li Yang, Anushya Subbiah, Hardik Patel, Judith Yue Li, Yanwei Song, Reza Mirghaderi, Vikram Aggarwal

cs.AI

摘要

大型語言模型（LLMs）在複雜對話理解、推理和編碼等任務上取得了極大成功，這要歸功於它們的新興能力。這些新興能力已通過多模態擴展，包括圖像、音頻和視頻功能。另一方面，推薦系統對於信息尋找和物品發現需求至關重要。最近，人們開始嘗試將LLMs應用於推薦系統。目前嘗試的一個困難是，基礎LLM通常未在推薦系統數據上進行訓練，該數據主要包含用戶交互信號，並且通常不公開。另一個困難是，用戶交互信號通常與自然語言文本具有不同的模式，目前尚不清楚LLM訓練設置是否能夠從交互信號中學習到比傳統推薦系統方法更多的非平凡知識。最後，訓練多個LLMs用於不同用例，並在從推薦系統數據中學習時保留原始語言和推理能力是困難的。為了解決這三個限制，我們提出了一種項目語言模型（ILM），它由一個項目編碼器和一個凍結的LLM組成。項目編碼器用於生成與文本對齊的項目表示，編碼用戶交互信號，而凍結的LLM則能夠理解這些項目表示，並保留預訓練知識。我們進行了大量實驗，這些實驗既證明了語言對齊的重要性，也證明了項目編碼器中用戶交互知識的重要性。

English

Large-language Models (LLMs) have been extremely successful at tasks like complex dialogue understanding, reasoning and coding due to their emergent abilities. These emergent abilities have been extended with multi-modality to include image, audio, and video capabilities. Recommender systems, on the other hand, have been critical for information seeking and item discovery needs. Recently, there have been attempts to apply LLMs for recommendations. One difficulty of current attempts is that the underlying LLM is usually not trained on the recommender system data, which largely contains user interaction signals and is often not publicly available. Another difficulty is user interaction signals often have a different pattern from natural language text, and it is currently unclear if the LLM training setup can learn more non-trivial knowledge from interaction signals compared with traditional recommender system methods. Finally, it is difficult to train multiple LLMs for different use-cases, and to retain the original language and reasoning abilities when learning from recommender system data. To address these three limitations, we propose an Item-Language Model (ILM), which is composed of an item encoder to produce text-aligned item representations that encode user interaction signals, and a frozen LLM that can understand those item representations with preserved pretrained knowledge. We conduct extensive experiments which demonstrate both the importance of the language-alignment and of user interaction knowledge in the item encoder.