在会话式推荐系统中利用大型语言模型

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

会话式推荐系统（CRS）通过实现用户与系统进行实时多轮对话，为用户提供了更高的透明度和控制权。最近，大型语言模型（LLMs）展现出了与世界知识和常识推理相结合的自然对话能力，释放了这一范式的潜力。然而，在CRS中有效利用LLMs会带来新的技术挑战，包括正确理解和控制复杂对话以及从外部信息源中检索信息。这些问题受到庞大、不断发展的项目语料库和缺乏用于训练的对话数据的影响。在本文中，我们提供了构建端到端大规模CRS的路线图，利用LLMs。具体来说，我们提出了用户偏好理解、灵活对话管理和可解释推荐的新实现，作为由LLMs驱动的集成架构的一部分。为了提高个性化，我们描述了LLM如何消化可解释的自然语言用户资料，并将其用于调节会话级上下文。为了克服在没有现有生产CRS的情况下的对话数据限制，我们提出了构建可控LLM用户模拟器的技术，以生成合成对话。作为概念验证，我们介绍了RecLLM，一个基于LaMDA构建的YouTube视频的大规模CRS，并通过一些示例对话展示了其流畅性和多样功能性。

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.