DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance Modeling

arXiv 2606.04374 ↗First posted 3 Jun 2026cs.IR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite rapid progress of continuous embeddings for e-commerce search relevance, a long-standing open problem is the difficulty in capturing fine-grained attribute distinctions. While discrete Semantic Identifiers (SIDs) have been widely adopted as a promising alternative, existing SID generation methods rely heavily on unsupervised quantization. In realistic scenarios, the lack of explicit supervision often makes it more difficult to dictate which items should share an SID, resulting in limited capability for query-dependent ranking. To address the issue of unsupervised SIDs, we propose to explicitly model discrete relevance features and develop a Discrete Semantic Identifier Relevance Model (DSIRM). Specifically, we present a query-bridged contrastive quantization approach on the item side, injecting query-item interaction supervision into Residual Quantization to actively learn relevance-aware semantic partitions. On the other hand, we explore generative LLMs on the query side to explicitly predict item SIDs from text, resolving tail queries and intent ambiguity. Hierarchical prefix matching between query and item SIDs yields discriminative features that perfectly complement dense signals. Extensive experimental results on Tmall's production data show that our proposed approach has achieved better results, improving offline AUC by +1.54%. Deployed via an efficient hybrid architecture, it achieves significant online lifts (+0.13% UCTR, +0.25% UCTCVR), proving its massive industrial value.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

24 of 34 references.

References · 24

2020Language Models are Few-Shot Learnerscited by 32,419
2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
2025Qwen3 Technical Reportcited by 8,820
2018Representation Learning with Contrastive Predictive Codingcited by 7,777
2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
2022Autoregressive Image Generation using Residual Quantizationcited by 722
2019Passage Re-ranking with BERTcited by 645
2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 413

12 more

2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 286
2022Transformer Memory as a Differentiable Search Indexcited by 247
2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 214
2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 173
2019Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoringcited by 165
2021Optimizing Dense Retrieval Model Training with Hard Negativescited by 155
2019Semantics-aware BERT for Language Understandingcited by 112
2022A Neural Corpus Indexer for Document Retrievalcited by 111
2019Semantic Product Searchcited by 51
2022Curriculum Learning for Dense Retrieval Distillationcited by 38
2020Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learningcited by 32

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way