@inproceedings{zou-etal-2025-multi,
    title = "Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification",
    author = "Zou, Huike  and
      Yang, Haiyang  and
      Su, Yindu  and
      Yu, Chen Li  and
      Xie, Qinye  and
      Lian, Chengbao  and
      Zhang, Qingheng  and
      Han, Shuguang  and
      Huang, Fei  and
      Chen, Jufeng",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.147/",
    pages = "2096--2105",
    ISBN = "979-8-89176-333-3",
    abstract = "Identifying attribute values from product profiles is a key task for improving product search, recommendation, and business analytics on e-commerce platforms, which we called Product Attribute Value Identification (PAVI) . However, existing PAVI methods face critical challenges, such as cascading errors, inability to handle out-of-distribution (OOD) attribute values, and lack of generalization capability. To address these limitations, we introduce Multi-Value-Product Retrieval-Augmented Generation (MVP-RAG), combining the strengths of retrieval, generation, and classification paradigms. MVP-RAG defines PAVI as a retrieval-generation task, where the product title description serves as the query, and products and attribute values act as the corpus. It first retrieves similar products of the same category and candidate attribute values, and then generates the standardized attribute values. The key advantages of this work are: (1) the proposal of a multi-level retrieval scheme, with products and attribute values as distinct hierarchical levels in PAVI domain (2) attribute value generation of large language model to significantly alleviate the OOD problem and (3) its successful deployment in a real-world industrial environment. Extensive experimental results on the dataset demonstrate that the proposed method performs better than the state-of-the-art baselines."
}