CORE：一种用于电子商务搜索的统一级联序数相关性估计框架
CORE: A Unified Cascaded Ordinal Relevance Estimation Framework for E-commerce Search
浏览论文内容
中文总结 AI 辅助
该研究针对电商搜索中排名相关性问题，提出统一级联二元分类框架，将相关性估计转为顺序决策过程。框架适用于大语言模型和在线BERT模型，经实验验证能显著提升相关性性能，降低在线坏例率，表明分层建模对相关性估计有效。
中文摘要 AI 辅助
排名相关性是电子商务搜索中的一项基本任务，直接影响排名质量和消费者体验。虽然本质上是一个序数分类问题，但通常被表述为传统的多类分类，这忽略了相关性水平之间的自然顺序，对相邻和遥远的错误分类给予相同的惩罚。这种不匹配导致实际相关性评估的学习目标次优。为了解决这个问题，我们提出了一个统一的级联二元分类框架，适用于大语言模型推理和基于在线BERT的推理，将相关性估计重新表述为一个顺序决策过程，并将多类预测分解为一系列从高到低相关性层级的有序二元判断。对于大语言模型，我们设计了一个带有剪枝策略和特定层级奖励函数的逐步推理过程；对于在线BERT模型，我们用多个层级二元分类器取代传统分类头，并将大语言模型的能力提炼到在线模型中。广泛的离线工业基准评估和在线A/B实验表明，所提出的框架显著提高了相关性性能，将在线坏例率降低了15.94%。进一步分析表明，分层建模对于相关性估计是有效的。
英文摘要
Ranking relevance is a fundamental task in e-commerce search, directly affecting ranking quality and consumer experience. Although inherently an ordinal classification problem, it is commonly formulated as conventional multi-class classification, which overlooks the natural order among relevance levels and assigns equal penalties to adjacent and distant misclassifications. This mismatch leads to suboptimal learning objectives for practical relevance evaluation. To address this issue, we propose a unified cascaded binary classification framework applicable to both large language model inference and online BERT-based inference, which reformulates relevance estimation as a sequential decision process and decomposes multi-class prediction into a series of ordered binary judgments from higher to lower relevance tiers. For large language models, we design a step-wise reasoning procedure with pruning strategies and tier-specific reward functions. For the online BERT model, we replace the conventional classification head with multiple level-wise binary classifiers and distill the capabilities of large language models into the online model. Extensive offline industrial benchmark evaluations and online A/B experiments demonstrate that the proposed framework substantially improves relevance performance, reducing the online bad-case rate by 15.94\%. Further analyses suggest that tier-wise modeling is effective for relevance estimation.
