Generative Retrieval with Preference Optimization for E-commerce Search

TL;DR

This paper introduces a novel generative retrieval framework for E-commerce search that leverages preference optimization and constrained beam search to improve accuracy, interpretability, and user engagement.

Contribution

It proposes a new generative retrieval approach tailored for E-commerce, integrating multi-span identifiers, preference alignment, and constraint-based search to address domain-specific challenges.

Findings

Achieves competitive performance on real-world datasets.

Demonstrates improved conversion rates in online A/B tests.

Enhances interpretability of retrieval results.

Abstract

Generative retrieval introduces a groundbreaking paradigm to document retrieval by directly generating the identifier of a pertinent document in response to a specific query. This paradigm has demonstrated considerable benefits and potential, particularly in representation and generalization capabilities, within the context of large language models. However, it faces significant challenges in E-commerce search scenarios, including the complexity of generating detailed item titles from brief queries, the presence of noise in item titles with weak language order, issues with long-tail queries, and the interpretability of results. To address these challenges, we have developed an innovative framework for E-commerce search, called generative retrieval with preference optimization. This framework is designed to effectively learn and align an autoregressive model with target data, subsequently generating the final item through constraint-based beam search. By employing multi-span identifiers to represent raw item titles and transforming the task of generating titles from queries into the task of generating multi-span identifiers from queries, we aim to simplify the generation process. The framework further aligns with human preferences using click data and employs a constrained search method to identify key spans for retrieving the final item, thereby enhancing result interpretability. Our extensive experiments show that this framework achieves competitive performance on a real-world dataset, and online A/B tests demonstrate the superiority and effectiveness in improving conversion gains.