GenRec: 迈向Netflix的LLM原生推荐

Authors: Ying Li, Arjun Rao, Shradha Sehgal

Introduction

引言

Recommendations sit at the heart of the Netflix experience. Our current production models rely on thousands of hand‑crafted features over users, items, and interactions, along with specialized architectures for sequence modeling, feature interactions, and multi‑task objectives. This stack has evolved over many years to support diverse content types (movies, series, games, live, podcasts) and product surfaces, but its complexity makes it costly to onboard new use cases: adding a content type or surface can require significant feature engineering, architecture change, infrastructure work, and experimentation.

推荐是 Netflix 体验的核心。我们当前的生产模型依赖于数千个针对用户、物品和交互的手工特征，以及用于序列建模、特征交互和多任务目标的专用架构。该技术栈经过多年发展，已支持多种内容类型（电影、剧集、游戏、直播、播客）和产品界面，但其复杂性使得引入新用例的成本很高：增加一种内容类型或界面可能需要大量的特征工程、架构更改、基础设施工作和实验。

At the same time, large language models (LLMs) are changing how we think about recommendation, as shown by recent work such as PLUM, GLIDE, and OneRec-Think. Their broad world knowledge and strong language understanding make it possible to represent user histories and item metadata directly as text, capture rich relationships in a shared semantic space, and steer recommendations via natural‑language prompts. However, off‑the‑shelf LLMs are still far from production‑ready recommenders: they often over‑recommend globally popular content, hallucinate out‑of‑catalog items, ignore business constraints, and provide only limited personalization.

与此同时，大型语言模型（LLMs）正在改变我们对推荐的思考方式，正如PLUM、GLIDE和OneRec-Think等近期工作所展示的那样。它们广泛的全球知识和强大的语言理解能力使得直接将用户历史和项目元数据表示为文本、在共享语义空间中捕获丰富关系以及通过自然语言提示引导推荐成为可能。然而，现成的LLMs距离生产就绪的推荐系统还有很大差距：它们经常过度推荐全球热门内容，幻觉出内容库之外的项目，忽略业务约束，并且仅提供有限的个性化。

To address this, we built GenRec, an LLM‑backed recommendation ranker that post‑trains an internal foundation LLM on Netflix‑specific data and objectives. GenRec shows that an LLM‑based ranker can match or exceed a mature production system while relying on far fewer labeled examples and input signals...