发表机构
Korea University; KT Corporation（高丽大学; KT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推荐系统中物品侧信息利用不足的问题，提出CAIRO框架，通过结构化元数据、轻量级画像器生成上下文特异性物品画像，提升了LLM重排序性能。
AI 中文摘要
尽管大语言模型（LLM）已显著推进了推荐系统的重排序任务，但有效利用物品侧信息仍具挑战性。现实中的物品由大量异构且非结构化的元数据描述，其中与决策相关的信号往往是隐式、含噪的，或被掩埋在冗长描述中。此外，特征显著性高度依赖上下文，不仅因物品而异，还因用户而异。现有方法通常依赖物品标题、固定属性或静态物品摘要，这限制了个性化和细粒度的物品理解。为弥合这一差距，我们提出CAIRO——一种面向基于LLM的重排序的用户上下文感知物品画像框架。CAIRO首先将原始元数据和评论结构化，分为客观特征和主观特质，并采用轻量级画像器为每个用户-物品对选择最相关的信息，且仅产生有限的服务时间开销。生成的画像简洁且具有上下文特异性，为LLM的排序决策提供相关的物品侧证据。实验表明，CAIRO可持续提升基于LLM的重排序性能，凸显了有效利用海量物品侧信息的物品画像的重要性。
英文摘要
While Large Language Models (LLMs) have significantly advanced reranking in recommendation, effectively leveraging item-side information remains challenging. Real-world items are described by vast, heterogeneous, and unstructured metadata, where decision-relevant signals are often implicit, noisy, or buried in long descriptions. Moreover, feature salience is highly context-dependent, varying not only across items but also across users. Existing methods often rely on item titles, fixed attributes, or static item summaries, which limit personalized and fine-grained item understanding. To bridge this gap, we propose CAIRO, a user context-aware item profiling framework for LLM-based reranking. CAIRO first structures raw metadata and reviews into objective features and subjective traits, and employs a lightweight profiler to select the most relevant information for each user-item pair with limited serving-time overhead. The resulting profiles are concise and context-specific, providing relevant item-side evidence for the LLM's ranking decision. Experiments show that CAIRO consistently improves LLM-based reranking, highlighting the importance of item profiling that effectively exploits vast item-side information.
CommentsAccepted to CIKM 2026
