@inproceedings{lu-etal-2026-lore,
    title = "{L}o{RE}: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment",
    author = "Lu, Chenji  and
      Chen, Zhuo  and
      Zhao, Hui  and
      Zeng, Zhiyuan  and
      Zhao, Gang  and
      Ren, Junjie  and
      Lihaoran  and
      Liu, Songyan  and
      Wang, Pengjie  and
      Yu, Chuan  and
      Xu, Jian  and
      Zheng, Bo",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1536/",
    pages = "30754--30768",
    ISBN = "979-8-89176-395-1",
    abstract = "E-commerce search relevance is a critical component of retrieval systems. While Large Language Models (LLMs)-driven Chain-of-Thought (CoT) modeling has become the dominant paradigm and yielded significant gains, a critical gap remains: the absence of a systematic definition for comprehensive relevance reasoning, which leads to significant blind spots in current approaches. In this paper, we deconstruct the task into three core competencies: reasoning knowledge, multi-modal understanding, and rule awareness. Accordingly, we propose LoRE(Large Generative Model for Search Relevance), a novel two-stage training framework. We first employ an SFT phase to instill these capabilities via a progressive CoT synthesis pipeline, followed by a Reinforcement Learning(RL) phase, which serves as a regularizer, pruning redundant logic to achieve precise and robust adjudication. Extensive experiments validate LoRE, outperforming GPT-5 by 29.1{\%} in Macro-F1 and achieving a 27{\%} online gain, offering a vital reference for industrial domain-specific post-training."
}