Metraipolis › archive › dc_4bc17bfec468

Generative Search and Recommendation at Shopify — arXiv:2611.08804

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.08804
License (as archived): CC0-1.0
Archived: 2026-11-09T22:44:54.143Z
SHA-256 of the archived text: cd333e7d25e446e1fc58e63386689aeb73c7a75da54ae0b9f51062a98174c832
Stable URL of this page: https://metraipolis.com/documento/dc_4bc17bfec468

How to cite

Generative Search and Recommendation at Shopify — arXiv:2611.08804 — arXiv (en), https://arxiv.org/abs/2611.08804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bc17bfec468 (Metraipolis archive dc_4bc17bfec468, sha256 cd333e7d25e446e1fc58e63386689aeb73c7a75da54ae0b9f51062a98174c832)

BibTeX

@misc{dc4bc17bfec468,
  title = {Generative Search and Recommendation at Shopify — arXiv:2611.08804},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08804},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bc17bfec468; sha256 cd333e7d25e446e1fc58e63386689aeb73c7a75da54ae0b9f51062a98174c832},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Search and recommendation at Shopify require retrieving relevant products from a changing catalog of billions of products under strict latency constraints. We present SID-LLM, which casts both tasks as generating semantic IDs: short sequences of content-derived tokens representing products. We jointly pre-train SID-LLM on catalog and behavioral data, giving search and recommendation a shared representation and training objective. We show that reinforcement learning further improves judged search relevance. Furthermore, distillation from task-specific experts improves recommendation quality over joint supervised fine-tuning without a statistically detected loss in search quality. Finally, for efficient serving, we pair multi-token prediction with a lightweight ranker, improving retrieval quality over our autoregressive baseline while reducing latency. We evaluate SID-LLM both as a standalone retriever and as a component of Shopify's production search and recommendation systems. As a standalone search system, SID-LLM achieves quality comparable to Shopify's existing multi-model search stack while meeting production latency requirements. Integrating SID-LLM into the search and recommendation stacks provides significant gains in both offline evaluations and online A/B tests. Together, these results demonstrate the practical value of semantic-ID generation as a unified approach to product discovery at scale.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2611.08804 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:37:32.233Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).