Learning When to Personalize: LLM Based Playlist Generation via Query Taxonomy and Classification

Fedor Buzaev, Ivan Sukharev, Rinat Mullahmetov, Roman Bogachev, Ilya Sedunov, Oleg Pavlovich, Daria Pugacheva


Abstract
Playlist generation based on textual queries using large language models (LLMs) is becoming an important interaction paradigm for music streaming platforms. User queries span a wide spectrum from highly personalized intent to essentially catalog-style requests. Existing systems typically rely on non-personalized retrieval/ranking or apply a fixed level of preference conditioning to every query, which can overfit catalog queries to a single user or under-personalize explicitly listener-dependent requests. We present an industrial-scale LLM-based playlist generation system with dynamic personalization that adapts the personalization strength to the query type. We define a query taxonomy, train a query-type classifier on 5,000 manually labeled queries, and use its predicted probability to modulate the mixture of LLM-based semantic scoring and personalized evaluation. In a blind user study with pairwise comparisons and ELO aggregation, this approach consistently outperforms both non-personalized and fixed-personalization baselines.
Anthology ID:
2026.nlp4musa-1.8
Volume:
Proceedings of the 4th Workshop on NLP for Music and Audio (NLP4MusA 2026)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Elena V. Epure, Sergio Oramas, SeungHeon Doh, Pedro Ramoneda, Anna Kruspe, Mohamed Sordo
Venues:
NLP4MusA | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
51–57
Language:
URL:
https://aclanthology.org/2026.nlp4musa-1.8/
DOI:
Bibkey:
Cite (ACL):
Fedor Buzaev, Ivan Sukharev, Rinat Mullahmetov, Roman Bogachev, Ilya Sedunov, Oleg Pavlovich, and Daria Pugacheva. 2026. Learning When to Personalize: LLM Based Playlist Generation via Query Taxonomy and Classification. In Proceedings of the 4th Workshop on NLP for Music and Audio (NLP4MusA 2026), pages 51–57, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Learning When to Personalize: LLM Based Playlist Generation via Query Taxonomy and Classification (Buzaev et al., NLP4MusA 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.nlp4musa-1.8.pdf