AI 中文总结
针对现有电商查询重排序器忽略组合需求约束的问题，提出REAlign框架，通过区分需求状态、优化排序，在电商基准上提升了重排序效果。
AI 中文摘要
组合式电商查询表达了多个必须同时满足的需求，然而现有的重排序器将这些约束简化为总体相关性，往往会优先推荐主题接近但不可行的商品。本文提出了一种名为REAlign的新型需求-证据对齐重排序框架，它明确将类型化的查询需求与可见证据关联起来。REAlign区分已满足、已违反和未被支持的条件，构建针对需求的对比以暴露失败模式，并通过需求感知组相对策略优化来优化无重复的部分排序。其列表效用在保留相关性的同时，纳入了需求满足度、证据支持度、实质性违反和输出有效性。在两个固定池电商基准上的实验显示，在匹配的训练预算下，REAlign相较于强大的监督学习和策略优化基线取得了持续的改进，在排名靠前的候选商品中违规情况更少，且在浅层排名时收益更大。受控消融实验证实了需求建模、证据接地和分解优化的互补价值。
英文摘要
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.
