arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12968cs.IRcs.AIcs.CL
收藏

RGAlign-Rec: 基于排名引导的潜在查询推理中的对齐方法

RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems

Forth AI Singapore(Forth AI新加坡);Shopee Singapore(Shopee新加坡);Singapore Uni. of Tech. and Design(新加坡技术与设计大学)

Junhua Liu, Yang Jihao, Cheng Chang, Kunrong LI, Bin Fu, Kwan Hui Lim

AI总结:

RGAlign-Rec通过闭环对齐框架结合语义推理和增强查询模型,提升电子商务推荐系统的预测准确性和服务质量。

摘要:

主动意图预测是现代电子商务聊天机器人中的关键能力,能够通过行为和上下文信号预测用户需求,实现"零查询"推荐。然而,现有工业系统面临两个根本性挑战:(1)离散用户特征与聊天机器人知识库中语义意图之间的语义鸿沟;(2)通用大语言模型(LLM)输出与任务特定的排序效用之间的目标不一致。为了解决这些问题,我们提出了RGAlign-Rec,一个闭环对齐框架,集成了基于LLM的语义推理器和增强查询(QE)排序模型。我们还引入了排名引导对齐(RGA),一种多阶段训练范式,利用下游排序信号作为反馈来优化LLM的潜在推理。在Shopee的大型工业数据集上的大量实验表明,RGAlign-Rec在GAUC上实现了0.12%的提升,导致错误率减少了3.52%,并在Recall@3上提高了0.56%。在线A/B测试进一步验证了我们框架的累积有效性:增强查询模型(QE-Rec)最初在CTR上提高了0.98%,而后续的排名引导对齐阶段贡献了额外的0.13%提升。这些结果表明,排名意识的对齐有效同步了语义推理与排序目标,显著提高了预测准确性和实际应用中的服务质量。

英文摘要:

Proactive intent prediction is a critical capability in modern e-commerce chatbots, enabling "zero-query" recommendations by anticipating user needs from behavioral and contextual signals. However, existing industrial systems face two fundamental challenges: (1) the semantic gap between discrete user features and the semantic intents within the chatbot's Knowledge Base, and (2) the objective misalignment between general-purpose LLM outputs and task-specific ranking utilities. To address these issues, we propose RGAlign-Rec, a closed-loop alignment framework that integrates an LLM-based semantic reasoner with a Query-Enhanced (QE) ranking model. We also introduce Ranking-Guided Alignment (RGA), a multi-stage training paradigm that utilizes downstream ranking signals as feedback to refine the LLM's latent reasoning. Extensive experiments on a large-scale industrial dataset from Shopee demonstrate that RGAlign-Rec achieves a 0.12% gain in GAUC, leading to a significant 3.52% relative reduction in error rate, and a 0.56% improvement in Recall@3. Online A/B testing further validates the cumulative effectiveness of our framework: the Query-Enhanced model (QE-Rec) initially yields a 0.98% improvement in CTR, while the subsequent Ranking-Guided Alignment stage contributes an additional 0.13% gain. These results indicate that ranking-aware alignment effectively synchronizes semantic reasoning with ranking objectives, significantly enhancing both prediction accuracy and service quality in real-world proactive recommendation systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑