让大模型更懂用户行为，自动优化推荐文本输入
From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation at Industry Scale
- 用强化学习训练智能代理，自动把用户日志转成最佳自然语言
- 在奈飞数据上提升93%推荐准确率，远超固定模板方法
- 适合做工业级推荐系统的大模型应用者参考
大型语言模型（LLM）是生成式推荐系统的核心，但关键挑战——将结构化用户交互日志转化为有效自然语言输入的「口语化」问题仍被忽视。现有方法依赖固定模板拼接字段，导致推荐表示效果不佳。本文提出一种以数据为中心的框架，通过强化学习训练一个口语化代理，将原始交互历史转化为优化后的文本上下文，以推荐准确率为训练信号。该代理学会过滤噪声、引入相关元数据并重新组织信息，从而提升下游预测性能。在奈飞大规模流媒体数据集上的实验表明，所学口语化方式相较模板基线，在发现类项目推荐准确率上最高提升93%。进一步分析揭示了用户兴趣总结、噪声去除和语法标准化等涌现策略，为构建高效LLM推荐系统提供了新见解。
原文摘要 · Abstract (English)
Large language models (LLMs) are promising backbones for generative recommender systems, yet a key challenge remains underexplored: verbalization, i.e., converting structured user interaction logs into effective natural language inputs. Existing methods rely on rigid templates that simply concatenate fields, yielding suboptimal representations for recommendation. We propose a data-centric framework that learns verbalization for LLM-based recommendation. Using reinforcement learning, a verbalization agent transforms raw interaction histories into optimized textual contexts, with recommendation accuracy as the training signal. This agent learns to filter noise, incorporate relevant metadata, and reorganize information to improve downstream predictions. Experiments on a large-scale industrial streaming dataset from Netflix show that learned verbalization delivers up to 93% relative improvement in discovery item recommendation accuracy over template-based baselines. Further analysis reveals emergent strategies such as user interest summarization, noise removal, and syntax normalization, offering insights into effective context construction for LLM-based recommender systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。