SPEAR: Selection-aware Personalized End-to-end Adaptive Rewriting and Retrieval for Community Search

2026-08-03

AI Summary

This work addresses the disconnection between query rewriting and retrieval in e-commerce search, which often leads to intent drift and shortcut reliance on overly generic terms. To bridge this gap, we propose SPEAR, an end-to-end framework that introduces, for the first time in community search, a selection-aware mechanism. SPEAR jointly optimizes personalized query rewriting and retrieval through a dual-embedding backbone, a multiplicative gating aggregator, and a dynamic rewrite selector. Gradient isolation mitigates semantic erosion, while the gating mechanism suppresses shortcut dependencies, enabling request-level adaptive rewriting and relevance calibration. Offline evaluations show an 18.2% improvement in rewrite semantic similarity@10 and a 99.5% gain in click recall@10. Online A/B tests demonstrate a 0.259% increase in query click-through rate and a 0.733 rise in average reading depth, leading to full deployment on the Dewu community search platform.

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.

Problem

• query reformulation
• community search
• intent faithfulness
• generic-word dominance
• retrieval alignment

Innovation

• query reformulation
• end-to-end retrieval
• personalized search
• gradient isolation
• dynamic rewrite selection