Guardado en:
Detalles Bibliográficos
Autores principales: Baikalov, Vladimir, Bagautdinov, Iskander, Muravyov, Sergey
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.13273
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910130104172544
author Baikalov, Vladimir
Bagautdinov, Iskander
Muravyov, Sergey
author_facet Baikalov, Vladimir
Bagautdinov, Iskander
Muravyov, Sergey
contents Generative retrieval with Semantic IDs (SIDs) assigns each item a discrete identifier and treats retrieval as a sequence generation problem rather than a nearest-neighbor search. While content-only SIDs are stable, they do not take into account user-item interaction patterns, so recent systems construct interaction-informed SIDs. However, as interaction patterns drift over time, these identifiers become stale, i.e., their collaborative semantics no longer match recent logs. Prior work typically assumes a fixed SID vocabulary during fine-tuning, or treats SID refresh as a full rebuild that requires retraining. However, SID staleness under temporal drift is rarely analyzed explicitly. To bridge this gap, we study SID staleness under strict chronological evaluation and propose a lightweight, model-agnostic SID alignment update. Given refreshed SIDs derived from recent logs, we align them to the existing SID vocabulary so the retriever checkpoint remains compatible, enabling standard warm-start fine-tuning without a full rebuild-and-retrain pipeline. Across three public benchmarks, our update consistently improves Recall@K and nDCG@K at high cutoffs over naive fine-tuning with stale SIDs and reduces retriever-training compute by approximately 8-9 times compared to full retraining.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13273
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Mitigating Collaborative Semantic ID Staleness in Generative Retrieval
Baikalov, Vladimir
Bagautdinov, Iskander
Muravyov, Sergey
Information Retrieval
Generative retrieval with Semantic IDs (SIDs) assigns each item a discrete identifier and treats retrieval as a sequence generation problem rather than a nearest-neighbor search. While content-only SIDs are stable, they do not take into account user-item interaction patterns, so recent systems construct interaction-informed SIDs. However, as interaction patterns drift over time, these identifiers become stale, i.e., their collaborative semantics no longer match recent logs. Prior work typically assumes a fixed SID vocabulary during fine-tuning, or treats SID refresh as a full rebuild that requires retraining. However, SID staleness under temporal drift is rarely analyzed explicitly. To bridge this gap, we study SID staleness under strict chronological evaluation and propose a lightweight, model-agnostic SID alignment update. Given refreshed SIDs derived from recent logs, we align them to the existing SID vocabulary so the retriever checkpoint remains compatible, enabling standard warm-start fine-tuning without a full rebuild-and-retrain pipeline. Across three public benchmarks, our update consistently improves Recall@K and nDCG@K at high cutoffs over naive fine-tuning with stale SIDs and reduces retriever-training compute by approximately 8-9 times compared to full retraining.
title Mitigating Collaborative Semantic ID Staleness in Generative Retrieval
topic Information Retrieval
url https://arxiv.org/abs/2604.13273