Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification

2025-09-28

AI Summary

Product Attribute Value Identification (PAVI) is critical for enhancing e-commerce search, recommendation, and business analytics, yet existing approaches suffer from cascading errors, poor out-of-distribution (OOD) value detection, and limited generalization. To address these challenges, we propose a multi-paradigm PAVI framework integrating retrieval, generation, and classification. Specifically, we design a hierarchical semantic retrieval mechanism that models products and attribute values as layered units; develop a category-constrained retrieval-augmented generation (RAG) pipeline—comprising similar-product retrieval, candidate-value extraction, and large language model–based generation; and introduce a ranking-generation synergy strategy to mitigate error propagation and improve OOD robustness. Evaluated in real-world industrial deployments, our method significantly outperforms state-of-the-art baselines, achieving superior accuracy, strong generalization across diverse categories and unseen values, and high practical utility.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Learning to Search
• Computer Vision: Image and Video Retrieval

Application Category

• Search and Retrieval-Augmented AI: Ad search and search for Web retail
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Applications of semantic technologies for improving search, browsing, recommendation, personalization

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 demonstrate that MVP-RAG performs better than the state-of-the-art baselines.

Problem

• Identifying attribute values from e-commerce product profiles
• Addressing cascading errors and out-of-distribution value challenges
• Improving generalization in product attribute value identification

Innovation

• Multi-level retrieval scheme for products and attribute values
• Large language model generates standardized attribute values
• Alleviates out-of-distribution problem through generation approach