# Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale

arXiv: https://arxiv.org/abs/2609.35285 · HTML: https://mlsanity.com/paper/2609.35285/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation](https://mlsanity.com/paper/2310.19488/) (2023)
- [PinnerFormer: Sequence Modeling for User Representation at Pinterest](https://mlsanity.com/paper/2205.04507/) (2022)
- [LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation](https://mlsanity.com/paper/2405.20646/) (2024)
- [PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence](https://mlsanity.com/paper/2503.02398/) (2025)
- [Language-Based User Profiles for Recommendation](https://mlsanity.com/paper/2402.15623/) (2024)
- [LLM-based User Profile Management for Recommender System](https://mlsanity.com/paper/2502.14541/) (2025)
- [TEARS: Textual Representations for Scrutable Recommendations](https://mlsanity.com/paper/2410.19302/) (2024)
- [LLM-Based User Personas for Recommendations at Scale](https://mlsanity.com/paper/2606.12198/) (2026)
- [High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learning](https://mlsanity.com/paper/2602.07333/) (2026)
- [DUET: Joint Exploration of User Item Profiles in Recommendation System](https://mlsanity.com/paper/2604.13801/) (2026)
- [Self-supervised User Profile Generation for Personalization](https://mlsanity.com/paper/2606.05336/) (2026)

## Abstract (arXiv)

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.