Research paper

Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval

Research from AlibabaPublished by Association for Computational LinguisticsOct 2026PDF

Explore search indexes in which document identifiers encode business ranking goals as well as meaning.

Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval cover

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Gui Ling, Zhihong Chen, Yu Li, Tong Xiong, Kunhai Lin, Kaixuan Zhang, Yuliang Yan, Dan Ou, Tanghaihong, Bo Zheng. Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track. © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/2026.emnlp-industry.38. Original PDF, unmodified.

CC BY 4.0

Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval

Related research.

Evaluating Differential Privacy Guarantees

qis: reproducible performance analytics and portfolio backtesting in Python

Metaxy: Record-Level Feature Metadata Management for Multimodal ML Pipelines