Metraipolis › archive › dc_780b37bba67a
Routing Between Generative and Collaborative User Profiles: A Serving-Time Gate for Controllable Novelty — arXiv:2609.39043
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39043
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:43:32.092Z
- SHA-256 of the archived text
e1da5f344ef2bfbca4b36dee2ac190e182e546496c6ae809281fccde87a7cc8d- Stable URL of this page
https://metraipolis.com/documento/dc_780b37bba67a
How to cite
Routing Between Generative and Collaborative User Profiles: A Serving-Time Gate for Controllable Novelty — arXiv:2609.39043 — arXiv (en), https://arxiv.org/abs/2609.39043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_780b37bba67a (Metraipolis archive dc_780b37bba67a, sha256 e1da5f344ef2bfbca4b36dee2ac190e182e546496c6ae809281fccde87a7cc8d)
BibTeX
@misc{dc780b37bba67a,
title = {Routing Between Generative and Collaborative User Profiles: A Serving-Time Gate for Controllable Novelty — arXiv:2609.39043},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39043},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_780b37bba67a; sha256 e1da5f344ef2bfbca4b36dee2ac190e182e546496c6ae809281fccde87a7cc8d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) enable rich semantic user profiles for recommendation, but such profiles are more expensive to generate and are not necessarily desirable to deploy uniformly. We study whether LLM-generated profiles can instead be invoked selectively within a production recommendation pipeline. Using a real-world streaming dataset covering movies, TV shows, and sports content, we train a serving-time routing gate that assigns each user to either a collaborative sequential recommendation model or a recommendation model driven by an LLM-generated profile. The gate uses only serving-time features and learns to identify users for whom profile-based routing can increase Novelty@10 while preserving ranking relevance. A routing threshold controls how aggressively users are sent to the generative model, exposing a tunable novelty--relevance trade-off. At an overall NDCG-loss budget of 5\%, the learned gate increases Novelty@10 by 6.5\% while routing 12.5\% of users, outperforming simple heuristic and random routing policies at comparable relevance cost. These results show that LLM-generated user profiles can serve as a controllable complement to collaborative recommendation, while results with non-generative semantic profiles indicate that the benefit stems from selective routing rather than LLM generation alone. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.39043 — 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 2026-10-07T14:16:56.034Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).