Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval
cs.IR, cs.AI
Submitted: 2026-08-31
Updated: 2026-08-31
Comments: Findings of EMNLP 2026. 22 pages, 10 figures, 7 tables
Code: https://github.com/zzzgm/CHAP
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Generative Retrieval (GR) has emerged as a promising paradigm by mapping queries directly to Semantic IDs (SIDs) with powerful representation capabilities for candidate items.
Terminology
Abstract
Generative Retrieval (GR) has emerged as a promising paradigm by mapping queries directly to Semantic IDs (SIDs) with powerful representation capabilities for candidate items. However, existing SIDs derived solely from item content create a semantic gap, failing to align dynamic query intents with static item representations. Furthermore, current generative paradigms rarely model user behavior sequences and are always bottlenecked by the high inference latency of beam-search autoregressive decoding. To address these challenges, we propose C ross-component H ierarchical semantic A lignment for P ersonalized generative retrieval (CHAP), a novel personalized GR framework from a hierarchical perspective. First, we design a Hierarchical Semantic Alignment module to align query's latent space with item's quantization path and synchronize multi-granular semantics. Second, we construct a personalized GR framework that models user behavior by synergizing discrete SIDs for structural guidance and continuous representations for fine-grained semantic refinement. Notably, we introduce a Residual Cascading Generation mechanism to restrict the costly multi-step Transformer Decoder to a single-pass inference, boosting inference throughput while mitigating information loss. Extensive experiments on three public datasets, one proprietary industrial dataset, and online A/B tests demonstrate CHAP's superiority, validating the effectiveness and practical value of our approach. The code is publicly available at https://github.com/zzzgm/CHAP.
Sources
- Mitigating Collaborative Semantic ID Staleness in Generative Retrieval
- Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval
- Differentiable Semantic ID for Generative Recommendation
- MLPs are Efficient Distilled Generative Recommenders
- End-to-End Semantic ID Generation for Generative Advertisement Recommendation
- A Survey of Generative Information Retrieval
- KuaiSearch: An E-Commerce Search Dataset with Authentic Queries and Product Texts for Recall, Ranking, and Relevance
- CAT-ID$^2$: Category-Tree Integrated Document Identifier Learning for Generative Retrieval In E-commerce
- CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Generative Retrieval as Dense Retrieval
- Document Expansion by Query Prediction
- Hi-Gen: Generative Retrieval For Large-Scale Personalized E-commerce Search
- Unleash the Potential of Long Semantic IDs for Generative Recommendation
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
- Generative Dense Retrieval: Memory Can Be a Burden
- Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
- UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG