EGR: Embedding-Native Generative Retrieval with a Shared LLM

2026-07-25

AI Summary

Existing generative retrieval methods in recommendation and advertising systems are hindered by quantization dependencies, unstable identifier vocabularies, and insufficient query-item alignment. This work proposes the Embedding-based Generative Retrieval (EGR) framework, which unifies generative retrieval and end-to-end embedding learning within a single shared large language model for the first time. EGR directly learns dense embeddings from item metadata and user interaction histories, enabling query-item alignment in a unified vector space. By eliminating reliance on traditional semantic IDs, the approach supports cold-start scenarios and multimodal inputs while simplifying system architecture. Experiments demonstrate that EGR outperforms current baselines on the Amazon Reviews dataset and exhibits strong scalability and cold-start performance on Snap DPA data, yielding a 2.91% improvement in online conversion rate upon deployment.

Abstract

Generative retrieval is increasingly popular in large-scale recommendation and advertising systems, yet current methods introduce practical complications. Semantic-ID methods rely on quantization, mutable identifier vocabularies, and token-to-item grounding; embedding-based pipelines train the item encoder separately from the query generator, which limits user-item alignment. We propose EGR, an Embedding-Native Generative Retrieval framework for recommendation and advertising. EGR uses a single shared LLM to learn item representations from item metadata and user representations from interaction histories in one embedding space. Items are indexed directly as dense vectors, and user histories are encoded as dense retrieval queries. Joint contrastive training groups related items and aligns queries with their target items. We evaluate EGR on public benchmarks, industrial data, and live deployment. EGR outperforms published baselines on Amazon Reviews; on Snap DPA, it scales with data, handles cold-start items, and benefits from multimodal input. In production, EGR delivers a +2.91% conversion-rate lift, simplifying system design while improving retrieval quality and ad performance.

Problem

• generative retrieval
• recommendation systems
• advertising systems
• user-item alignment
• embedding-based retrieval

Innovation

• Generative Retrieval
• Shared LLM
• Embedding-Native
• Contrastive Training
• Cold-Start Handling