发表机构
Meta Platforms, Inc.（Meta平台公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对LLM时代推荐系统升级难题，提出LIGE-GR框架，将逐点排序系统泛化为列表式生成，在保持兼容性的同时提升短视频推荐时长，验证于Instagram Reels和Facebook Video。
AI 中文摘要
大型语言模型（LLM）的巨大成功为下一代推荐系统提供了重要启示。从结构上看，推荐与语言生成具有相似性：两者都旨在生成一个优化用户体验的有序序列。然而，如何将LLM范式的精髓精确地融入成熟的工业推荐系统仍是一个开放问题。这面临两个挑战。首先，尚不清楚如何将LLM范式中的序列级生成与优化引入推荐。其次，现实世界的推荐系统是成熟系统，多年来已围绕特定产品、业务约束、服务基础设施和组织归属进行了迭代定制。彻底替换此类系统在技术上往往存在风险，在组织上也会造成混乱。在本文中，我们提出LIGE-GR，一种从基于逐项推荐的传统排序系统升级到生成式推荐范式的列表式生成与评估推荐框架。LIGE-GR并非从头重建整个推荐栈，而是将现有的逐点推荐系统泛化为列表式生成系统。这使得成熟的推荐系统能够受益于列表式优化，同时保持与现有模型、价值函数和服务基础设施的兼容性。我们在Instagram Reels和Facebook Video的短视频推荐中验证了LIGE-GR。在这些推荐场景中，LIGE-GR使Instagram Reels上的用户时长提升了1.14%，Facebook Video上提升了0.72%，且仅需适度的额外推理资源。
英文摘要
The remarkable success of large language models (LLMs) has provided important inspiration for the next generation of recommender systems. Structurally, recommendation and language generation share a similarity: both aim to produce an ordered sequence that optimizes the user's experience. However, how to precisely absorb the essence of the LLM paradigm into mature industrial recommender systems remains an open problem. There are two challenges. First, it is unclear how to incorporate the LLM paradigm -- sequence-level generation and optimization -- into recommendation. Second, real-world recommender systems are mature systems that have been iteratively customized for years around specific products, business constraints, serving infrastructure, and organizational ownership. Replacing such systems wholesale is often technically risky and organizationally disruptive. In this paper, we propose LIGE-GR, a listwise generation and evaluation recommendation framework that upgrades from a traditional ranking system (itemwise recommendation) toward a generative recommendation paradigm. Instead of rebuilding the entire recommendation stack from scratch, LIGE-GR generalizes the existing pointwise recommendation system into a listwise generation system. This allows mature recommender systems to benefit from listwise optimization while preserving compatibility with existing models, value functions, and serving infrastructure. We validate LIGE-GR in short-video recommendation on Instagram Reels and Facebook Video. On these recommendation surfaces, LIGE-GR improves time spent by 1.14 percent on Instagram Reels and 0.72 percent on Facebook Video, while requiring only modest additional inference resources.
