Metraipolis › archive › dc_a6dbae3438d2

Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale — arXiv:2609.35285

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35285
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:39.303Z
SHA-256 of the archived text
a21bce1872fdc21ee4c81fe18853f1fd0f7c20c15bd5b2e8e2d51b0712e531bf
Stable URL of this page
https://metraipolis.com/documento/dc_a6dbae3438d2

How to cite

Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale — arXiv:2609.35285 — arXiv (en), https://arxiv.org/abs/2609.35285 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6dbae3438d2 (Metraipolis archive dc_a6dbae3438d2, sha256 a21bce1872fdc21ee4c81fe18853f1fd0f7c20c15bd5b2e8e2d51b0712e531bf)
BibTeX
@misc{dca6dbae3438d2,
  title = {Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale — arXiv:2609.35285},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35285},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6dbae3438d2; sha256 a21bce1872fdc21ee4c81fe18853f1fd0f7c20c15bd5b2e8e2d51b0712e531bf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35285. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Foundation model recommender systems require user context that can be consumed by large language models, reasoned over, and refined through natural-language interaction. Traditional behavioral embedding vectors remain highly effective for retrieval and ranking, but they are opaque to users and not natively expressed for language model workflows. We present Textual User Taste, a system that generates structured natural-language taste profiles from listening behavior, interaction signals, content metadata, and optional user feedback, and deploys them to millions of Spotify users. We describe the end-to-end production lifecycle required to generate, evaluate, optimize, and maintain these representations at industrial scale, including prompt development and compression, user steering, and integration with downstream personalization systems. Because no unique ground-truth taste profile exists, we introduce a multi-faceted evaluation framework to evaluate taste profiles as a production representation: they carry user-specific predictive signal independently, and when integrated with behavioral embeddings, improve MRR by 0.6% for future-track prediction and NDCG@7 by 2.2% for search ranking. Our evaluation also reveals that taste profiles support positive natural-language steering, while exposing important limitations, including challenges with negation and short-term temporal adaptation. These findings position taste profiles not as replacements for behavioral embeddings, but as an interpretable and steerable interface between evolving user context and foundation-model recommender systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35285 — 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 2026-10-07T20:29:01.818Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).