Sep 2026· Proceedings of the 20th ACM Conference on Recommender Systems· 0 citations· 12 references
TL;DR
This work proposes PLAIN, which integrates Multi-stage Codebook Construction (MCC) and Unified Generative Retrieval (UGR), and operationalizes the MCC schema by employing Symmetric Context Encoders that align both query and item representations to the structured label space via knowledge distillation and semi-supervised hierarchical quantization, enabling consistent end-to-end generative retrieval.
Abstract
Industrial search platforms must efficiently retrieve relevant items from billions of candidates while satisfying both query relevance and user preferences. Generative Search (GS) has emerged as a transformative paradigm that reformulates traditional indexing and matching as an autoregressive generation task. However, most existing generative search models suffer from two critical deficiencies: (1) generated Semantic IDs (SIDs) often lack explicit semantic correspondences, undermining codebook interpretability; (2) unstructured codebooks impose a fully-connected search space, forcing the generator to navigate a highly entangled decoding path. To address these limitations, we propose PLAIN, which integrates Multi-stage Codebook Construction (MCC) and Unified Generative Retrieval (UGR). MCC leverages LLM-generated taxonomy and metadata labels, applying hard assignment for closed-set taxonomy levels and soft assignment for open-set metadata levels, transforming unstructured codebooks into interpretable hierarchical topic paths. UGR operationalizes the MCC schema by employing Symmetric Context Encoders (SCE) that align both query and item representations to the structured label space via knowledge distillation and semi-supervised hierarchical quantization, enabling consistent end-to-end generative retrieval. Extensive experiments and online A/B testing in Kuaishou’s live search system demonstrate significant improvements in user engagement and content consumption.
A Hierarchical Semantic Alignment module to align query's latent space with item's quantization path and synchronize multi-granular semantics, and a personalized GR framework that models user behavior by synergizing discrete SIDs for structural guidance and continuous representations for fine-grained semantic refinemen...
Gao-Ming Zhang, Ang-Qing Jiang, Jian-Chun Song et al.· 0 citations
The results demonstrate that retrieval quality acts as a rigid performance ceiling for generative correctness and suggest that for RAG applications, strategic database indexing is a more critical performance lever than embedding parameter scale: architectural retrieval decisions matter more than model size.
Assmaa Moutaoukkil, A. El Mezouary, A. Idarrou et al.· EPJ Web of Conferences· 0 citations
Codebook-based semantic IDs (SIDs), short discrete code sequences produced by quantization over item representations, made generative recommendation practical by turning catalog-scale retrieval into low-cardinality generation. Yet the same interface now concentrates the field’s hardest questions. We revisit the canonic...
Danil Gusak, Evgeny Frolov· Proceedings of the 20th ACM...· 3 citations
This study proposes STaR, a novel retriever fine-tuning framework that integrates BM25 similarity graph-based soft labeling with a triplet similarity learning strategy based on Sentence-BERT (SBERT), and introduces a triplet-aware SBERT training architecture that explicitly models relative semantic distances between qu...
Jiali Jiang, Chih-Yung Chang, Youxi Li et al.· Multimedia Systems· 0 citations
ANGLE integrates retrieval, relevance, and ranking directly within a single LLM, enabling precise and efficient ranking of ads by leveraging the full capabilities of the LLM.
Tong-Tong Liu, Ren-Yu Zhang, Jia-Yu Ding et al.· 0 citations
Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can bridge vocabulary gaps with the target corpus. Any single LLM, however, is limited by its training data and architectural biases, and its enrichment behavior depends on h...
Tzu-I Ho, Yung-Yu Shih, Shang-Yu Su et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.