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.

翻译：对话推荐系统（CRS）通过让用户以实时多轮对话形式与系统交互，提供了更高的透明度和控制权。近年来，大型语言模型（LLM）展现出前所未有的自然对话能力，能将世界知识与常识推理融入语言理解，释放了这一范式的潜力。然而，在CRS中有效利用LLM带来了新的技术挑战，包括正确理解和控制复杂对话，以及从外部信息源检索内容。这些问题因不断扩展的大型物品语料库和缺乏训练用的对话数据而加剧。本文为使用LLM构建端到端大规模CRS提供了路线图。具体而言，我们提出了以LLM为核心的集成架构中用户偏好理解、灵活对话管理与可解释推荐的新实现方案。为提升个性化，我们描述了LLM如何消耗可解释的自然语言用户画像，并用其调节会话级上下文。为解决缺乏现有生产环境中CRS导致的对话数据限制问题，我们提出了一种构建可控LLM用户模拟器以生成合成对话的技术。作为概念验证，我们介绍了基于LaMDA为YouTube视频构建的大规模CRS——RecLLM，并通过若干示例对话展示了其流畅性与多样化功能。