Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval
Ming Pang, Chunyuan Yuan, Xiaoyu He, Zheng Fang, Donghao Xie, Fanyi Qu, Xue Ling Jiang, Changping Peng, Zhangang Lin, Zheng Luo, Jingping Shao · 2025
The retrieval module is a crucial component of search systems. Traditional sparse and dense retrieval methods struggle to leverage general world knowledge and often fail to capture the nuanced features of queries and products. With the advent of large language models (LLMs), industrial search systems have started to employ LLMs to generate identifiers for product retrieval. Commonly used identifiers include (1) static/semantic IDs and (2) product term sets. The first approach requires creating a product ID system from scratch, missing out on the world knowledge embedded within LLMs. While the second approach leverages this general knowledge, the significant difference in word distribution between queries and products means that product-based identifiers often do not align well with user search queries, leading to missed product recalls. Furthermore, when queries contain numerous attributes, these algorithms generate a large number of identifiers, making it difficult to assess their quality, which results in low overall recall efficiency.