面向决策的推荐重排序：Jev的实证研究

中文摘要 AI 辅助

大语言模型（LLMs）在推荐重排序方面展现出潜力，但其使用引入了推荐质量与服务效率之间的重要权衡。我们研究了当重排序任务本质上是预定义候选项目之间的结构化选择时，面向决策的模型是否能提供一种有用的替代方案。具体而言，我们对Jev进行了一项受控实证研究，Jev被TypeSafe AI描述为一种“系统一模型”，用于个性化推荐重排序，并将其与推荐专用模型以及点式和列表式Qwen重排序器在多个Amazon Reviews领域和候选集规模下进行比较，同时评估推荐效果和观察到的服务延迟。我们的结果表明，相对于所评估的基线，Jev保持了较强的推荐效果，同时其延迟增长比点式Qwen重排序器更为平缓，尽管其观察到的服务延迟仍显著高于推荐专用模型。综合来看，这些特性使Jev在候选规模和领域上处于一个独特的质量-延迟运行区间。这些发现促使进一步研究面向决策的模型在推荐及其他具有结构化输出空间的排序任务中的应用。

英文摘要

Large language models (LLMs) have shown promise for recommendation reranking, but their use introduces an important tradeoff between recommendation quality and serving efficiency. We investigate whether a decision-oriented model provides a useful alternative when the reranking task is fundamentally a structured choice among predefined candidate items. Specifically, we conduct a controlled empirical study of Jev, described by TypeSafe AI as a ``System One Model,'' for personalized recommendation reranking and compare it with recommendation-specific models and pointwise and listwise Qwen rerankers across multiple Amazon Reviews domains and candidate-set sizes, evaluating both recommendation effectiveness and observed serving latency. Our results show that Jev maintains strong recommendation effectiveness relative to the evaluated baselines while exhibiting substantially more gradual latency growth than the pointwise Qwen rerankers, although its observed serving latency remains substantially higher than that of recommendation-specific models. Together, these characteristics place Jev in a distinct quality--latency operating regime across candidate sizes and domains. These findings motivate further investigation of decision-oriented models for recommendation and other ranking tasks with structured output spaces.

发表机构

• Singapore Management University（新加坡管理大学）
• Meta AI

机构由 AI 辅助整理，请以论文原文为准。