深度思考，快速行动：多视角链式推理的潜在推理蒸馏用于电子商务相关性
Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance
AI总结：
本文提出多视角链式推理蒸馏方法，通过改进的教师模型和轻量级学生模型提升电子商务搜索相关性建模的准确性和效率。
摘要：
有效的相关性建模对于电子商务搜索至关重要，因为它将搜索结果与用户意图对齐，并提升客户体验。最近的工作利用大语言模型（LLMs）来解决传统相关性模型的局限性，特别是针对长尾和模糊查询。通过整合链式推理（CoT）推理，这些方法通过多步骤推理提高了准确性和可解释性。然而，仍然存在两个关键限制：（1）大多数现有方法依赖于单视角的CoT推理，这无法捕捉电子商务相关性的多面性（例如，用户意图与属性级匹配与业务特定规则）；（2）尽管CoT增强的LLM提供了丰富的推理能力，但其高推理延迟需要知识蒸馏以实现实时部署，然而当前的蒸馏方法在推理时丢弃了CoT推理结构，将其作为临时辅助信号，并放弃了其推理效用。为了解决这些挑战，我们提出了一种新的框架，更有效地利用CoT语义在整个优化管道中。具体来说，教师模型利用多视角CoT（MPCoT）生成多样化的推理依据，并结合监督微调（SFT）与直接偏好优化（DPO）来构建一个更稳健的推理器。在蒸馏方面，我们引入了潜在推理知识蒸馏（LRKD），它使学生模型具备轻量级的推理时间潜在推理提取器，允许高效且低延迟地内化LLM的复杂推理能力。在离线实验和在线A/B测试中评估了该方法，测试平台服务于每天数千万用户，我们的方法在离线实验中取得了显著的收益，显示出在商业表现和用户体验方面的明显优势。
英文摘要：
Effective relevance modeling is crucial for e-commerce search, as it aligns search results with user intent and enhances customer experience. Recent work has leveraged large language models (LLMs) to address the limitations of traditional relevance models, especially for long-tail and ambiguous queries. By incorporating Chain-of-Thought (CoT) reasoning, these approaches improve both accuracy and interpretability through multi-step reasoning. However, two key limitations remain: (1) most existing approaches rely on single-perspective CoT reasoning, which fails to capture the multifaceted nature of e-commerce relevance (e.g., user intent vs. attribute-level matching vs. business-specific rules); and (2) although CoT-enhanced LLM's offer rich reasoning capabilities, their high inference latency necessitates knowledge distillation for real-time deployment, yet current distillation methods discard the CoT rationale structure at inference, using it as a transient auxiliary signal and forfeiting its reasoning utility. To address these challenges, we propose a novel framework that better exploits CoT semantics throughout the optimization pipeline. Specifically, the teacher model leverages Multi-Perspective CoT (MPCoT) to generate diverse rationales and combines Supervised Fine-Tuning (SFT) with Direct Preference Optimization (DPO) to construct a more robust reasoner. For distillation, we introduce Latent Reasoning Knowledge Distillation (LRKD), which endows a student model with a lightweight inference-time latent reasoning extractor, allowing efficient and low-latency internalization of the LLM's sophisticated reasoning capabilities. Evaluated in offline experiments and online A/B tests on an e-commerce search advertising platform serving tens of millions of users daily, our method delivers significant offline gains, showing clear benefits in both commercial performance and user experience.
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。
