让电商搜索更懂复杂需求，精准匹配真实商品。
Requirement--Evidence Alignment for Compositional E-Commerce Queries
- 将查询需求与商品证据显式对齐，区分满足、违反和无支持的情况。
- 在两个基准上提升排序效果，顶部结果违规率更低，浅层排名增益显著。
- 适合需要精准理解多条件查询的电商搜索系统开发者。
复合型电商查询需同时满足多个条件，但现有重排序模型常将约束合并为整体相关性，导致推荐主题近似而非可行商品。本文提出REAlign框架，显式关联查询中的类型化需求与可见证据，区分满足、违反和无支持状态，构建针对性对比揭示失败模式，并通过需求感知的组相对策略优化实现去重的部分排序。其列表效用兼顾相关性与需求满足度、证据支持、材料违规和输出有效性。在两个固定池电商基准上的实验表明，在相同训练预算下，相比强监督与策略优化基线，性能持续提升，顶部候选违规减少，浅层排名收益更大。受控消融实验验证了需求建模、证据锚定与分解优化的互补价值。
原文摘要 · Abstract (English)
Compositional e-commerce queries express multiple requirements that must hold jointly, yet existing rerankers collapse these constraints into aggregate relevance and often promote topical near misses over feasible products. In this paper, we introduce REAlign, a novel requirement-evidence-aligned reranking framework that explicitly connects typed query requirements with visible evidence. REAlign distinguishes satisfied, violated, and unsupported conditions, constructs requirement-targeted contrasts that expose failure modes, and optimizes duplicate-free partial rankings through Requirement-Aware Group-Relative Policy Optimization. Its list utility preserves relevance while incorporating requirement satisfaction, evidence support, material violations, and output validity. Experiments on two fixed-pool e-commerce benchmarks show consistent improvements over strong supervised and policy-optimization baselines under matched training budgets, with fewer violations among top-ranked candidates and larger gains at shallow ranks. Controlled ablations confirm the complementary value of requirement modeling, evidence grounding, and decomposed optimization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。