arXiv cs.CL· Varun Joshi, Eva C. Song, ChengXiang Zhai·· 9 天前AI 评分18
语言模型用于电商搜索的页面级布局决策
Language Models for Page-Level Layout Decisions in E-commerce Search
AI 导读
研究用语言模型离线评估电商搜索页面布局决策，即是否在特定位置插入次级商品堆栈。对比直接提示词评判、提示词衍生特征和表征三种方法，表征方法在预测用户参与度上持续优于提示词评判，可作为电商搜索离线布局评估的可靠基础。该工作已被 ACM RecSys 2026 的 OARS Workshop 接收。
正文 · 原文
Abstract:E-commerce search pages are critical touchpoints for millions of online shoppers. While traditional search engines return a ranked list of results, modern E-commerce search pages increasingly incorporate recommender system modules -- for example, secondary stacks that surface alternative product groupings at specific positions. When introduced appropriately, secondary stacks can improve user engagement; however, suboptimal placement may disrupt browsing flow and degrade the primary results. Unlike traditional search ranking, where evaluation techniques such as interleaving are well established, evaluating page-level layout changes e.g., when and where to insert a secondary stack remains challenging without costly online A/B testing. To address this, we study offline methods for evaluating whether a given layout decision -- specifically, the inclusion of a secondary stack at a particular position -- is beneficial to users. We investigate language models as scalable evaluators by comparing direct prompt-based, prompt-derived feature, and representation-based methods. Our results show that representation-based approaches consistently outperform prompt-based judging in predicting user engagement, suggesting they provide a reliable foundation for offline layout evaluation in E-commerce search.
| Comments: | Accepted at the OARS Workshop, ACM RecSys 2026 |
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.10920 [cs.LG] |
| (or arXiv:2610.10920v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10920 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Varun Joshi [view email]
[v1]
Wed, 7 Oct 2026 21:19:47 UTC (1,557 KB)
来源：arXiv cs.CL · arxiv.org