发表机构
State Key Laboratory for Novel Software Technology, Nanjing University; School of Intelligence Science and Technology, Nanjing University; Taobao & Tmall Group of Alibaba（南京大学计算机软件新技术国家重点实验室; 南京大学智能科学与技术学院; 阿里巴巴淘宝天猫集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对转化归因接触点选择的语义差距问题，评估LLMs识别隐藏关联的能力，分析提示策略与模型选择的影响，还将LLM归因标签用于提升CVR模型性能。
AI 中文摘要
转化归因中的接触点选择，即识别促成转化的有意义接触点，对电商推荐和在线广告至关重要。当前选择方法严重依赖基于协同过滤的启发式规则，无法与用户感知的语义意图对齐。通过人工标注，我们发现存在显著的语义差距：许多隐含相关、语义相关的接触点未被现有规则检测到。因此，我们系统评估了大型语言模型（LLMs）识别这些隐藏关联的能力。评估显示，LLMs虽能有效发现大量隐含相关的接触点，但选择性能仍有较大提升空间。此外，我们分析了不同提示策略和基础模型选择对识别性能的影响，为其推理模式和有效性提供了宝贵见解。这些见解为转化归因从机械规则匹配向与人类对齐的语义推理过渡提供了新路线图。此外，我们利用LLM归因的转化标签增强工业级CVR模型训练，取得了显著的离线性能提升，展现了LLMs在转化归因中的潜力。
英文摘要
Touchpoint selection in conversion attribution, namely identifying meaningful touchpoints contributing to conversions, is essential for e-commerce recommendation and online advertising. Current selection methods rely heavily on collaborative-filtering-based heuristics, which fail to align with user-perceived semantic intent. Through human annotation, we reveal a significant semantic gap: many implicitly-related, semantically relevant touchpoints remain undetected by existing rules. Therefore, we systematically evaluate the capability of Large Language Models (LLMs) in identifying these hidden associations. Our evaluation shows that while LLMs effectively uncover a substantial portion of implicitly-related touchpoints, significant room for improvement remains in their selection performance. Furthermore, we analyze the impact of different prompting strategies and foundation model choices on identification performance, providing valuable insights into their reasoning patterns and effectiveness. These insights offer a new roadmap for transitioning conversion attribution from mechanical rule-matching to human-aligned semantic reasoning. Moreover, we leverage the LLM-attributed conversion labels for enhancing industrial CVR model training and achieve significant offline performance gains, showing the potential of LLMs in conversion attribution.
Comments6 pages, 4 figures, 3 tables; accepted as a short paper at CIKM 2026
