When LLM-Based User Profiling Adds Value in Production Streaming Recommendation

2026-09-22

AI Summary

研究对比了基于LLM和聚合方法的用户画像策略在流媒体推荐中的效果，探讨了不同策略在准确性、推荐质量及时间窗口设置上的差异。

Abstract

Personalized recommendation depends critically on how user representations are constructed from historical behavior. Two paradigms have emerged for constructing semantic user profiles in content-based recommendation. First, aggregate methods derive user representations as numerical aggregates of semantic item embeddings. Second, LLM-based methods generate natural-language summaries of user preferences and encode them through a text encoder. Each paradigm can be combined with temporal disentanglement of recent versus historical behavior. LLM-based profile generation is significantly more expensive than aggregate approaches, raising the question of when this additional cost is justified. We present a systematic comparison of four semantic user-profiling strategies, factorially crossed across representation type and temporal handling, evaluated on a real-world production dataset. The comparison reveals how these strategies differ across user behavior types, across both accuracy and beyond-accuracy dimensions of recommendation quality, and across the temporal-window setting that governs the disentanglement.

Problem

• LLM-based User Profiling
• Content-based Recommendation
• User Representations

Innovation

• LLM-based user profiling
• temporal disentanglement
• semantic user profiles
• personalized recommendation