在對話式推薦系統中利用大型語言模型

Leveraging Large Language Models in Conversational Recommender Systems

May 13, 2023

作者: Luke Friedman, Sameer Ahuja, David Allen, Terry Tan, Hakim Sidahmed, Changbo Long, Jun Xie, Gabriel Schubiner, Ajay Patel, Harsh Lara, Brian Chu, Zexi Chen, Manoj Tiwari

cs.AI

摘要

一個對話式推薦系統（CRS）通過實時多輪對話使用戶能夠與系統互動，從而提供更高的透明度和控制權。最近，大型語言模型（LLMs）展示了與世界知識和常識推理相結合的自然對話能力，開啟了這一範式的潛力。然而，在 CRS 內有效地利用 LLMs 會引入新的技術挑戰，包括正確理解和控制複雜對話以及從外部信息來源檢索。這些問題受到大型、不斷發展的項目語料庫和缺乏用於訓練的對話數據的加劇。在本文中，我們提供了一個使用 LLMs 構建端到端大規模 CRS 的路線圖。具體而言，我們提出了用於用戶偏好理解、靈活對話管理和可解釋推薦的新實現，作為由 LLMs 驅動的集成架構的一部分。為了改善個性化，我們描述了一個 LLM 如何消化可解釋的自然語言用戶檔案並將其用於調節會話級上下文。為了克服在缺乏現有生產 CRS 的情況下的對話數據限制，我們提出了建立可控 LLM 為基礎的用戶模擬器的技術，以生成合成對話。作為概念證明，我們介紹了 RecLLM，一個基於 LaMDA 的 YouTube 視頻大規模 CRS，並通過一些說明性示例對話展示了其流暢性和多樣功能性。

English

A Conversational Recommender System (CRS) offers increased transparency and control to users by enabling them to engage with the system through a real-time multi-turn dialogue. Recently, Large Language Models (LLMs) have exhibited an unprecedented ability to converse naturally and incorporate world knowledge and common-sense reasoning into language understanding, unlocking the potential of this paradigm. However, effectively leveraging LLMs within a CRS introduces new technical challenges, including properly understanding and controlling a complex conversation and retrieving from external sources of information. These issues are exacerbated by a large, evolving item corpus and a lack of conversational data for training. In this paper, we provide a roadmap for building an end-to-end large-scale CRS using LLMs. In particular, we propose new implementations for user preference understanding, flexible dialogue management and explainable recommendations as part of an integrated architecture powered by LLMs. For improved personalization, we describe how an LLM can consume interpretable natural language user profiles and use them to modulate session-level context. To overcome conversational data limitations in the absence of an existing production CRS, we propose techniques for building a controllable LLM-based user simulator to generate synthetic conversations. As a proof of concept we introduce RecLLM, a large-scale CRS for YouTube videos built on LaMDA, and demonstrate its fluency and diverse functionality through some illustrative example conversations.