SPEAR: Selection-aware Personalized End-to-end Adaptive Rewriting and Retrieval for Community Search
2026-08-03 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors identify a problem in e-commerce search where rewriting user queries and retrieving items are treated separately, causing mismatches. Existing models often produce generic rewrites that lose the original query’s intent. To fix this, the authors propose SPEAR, a system that carefully balances rewrite quality and item relevance by using a dual-embedding method, a gating mechanism, and a dynamic selector tailored to each query. Their tests show SPEAR significantly improves search results and user engagement, and the system is now live on Dewu's platform.
query reformulatione-commerce searchretrieval effectivenessdual-embeddingclick-through rate (CTR)gating mechanismdynamic selectorsemantic similarityA/B testinguser engagement
Authors
Wenbin Wu, Yuzhong Wu, Yufan Xu, Kuan Fang, Xing Xu, Cheng Ye, Xiaobin Hu
Abstract
Query reformulation bridges user intent and retrieval in e-commerce search, yet production systems optimize rewrite quality and retrieval effectiveness separately, leaving the two stages structurally misaligned. Path-based architectures unify them end-to-end but were designed for personalization, where relevance is not an explicit constraint-search additionally requires the rewrite to remain faithful to the user's stated query intent. Transplanted directly, these models learn a shortcut we term the generic-word dominance effect: they favor generic rewrites that score well on paths but drift from query intent. To address this, we propose SPEAR (Selection-aware Personalized End-to-end Adaptive Rewriting and Retrieval), which integrates three components that each target one failure mode: (1) a dual-embedding backbone with auxiliary loss and gradient isolation that shields recall-side semantics from being eroded by CTR-driven ranking signals; (2) a multiplicative gating aggregator that lets a rewrite score high only when both its confidence and item relevance are strong, eliminating the generic-word shortcut; (3) a Dynamic Rewrite Selector that jointly generates request-specific rewrite weights and user-query-conditioned scale and bias terms, allowing both rewrite preference and relevance calibration to adapt to each request. Offline evaluation on 100K held-out industrial search sessions shows that the proposed framework improves rewrite semantic similarity@10 by +18.2 and click recall@10 by +99.5 over the production baseline. In online A/B testing, SPEAR achieves +0.259 in query-view CTR and +0.733 in average reading depth, confirming that improved rewrite selection translates into stronger retrieval and deeper user engagement. The proposed SPEAR system has been fully deployed in Dewu's community search platform since 2025. Our code is available at https://github.com/mallocagi1-cell/spear.