Deploying Semantic ID-based Generative Retrieval for Large-Scale Podcast Discovery at Spotify

• URL: http://arxiv.org/abs/2603.17540v1
• Date: Wed, 18 Mar 2026 09:46:10 GMT
• Title: Deploying Semantic ID-based Generative Retrieval for Large-Scale Podcast Discovery at Spotify
• Abstract summary: We develop a production-scale generative recommender for podcast discovery at Spotify.<n>GLIDE formulates recommendation as an instruction-following task over a discretized catalog using Semantic IDs.<n>We show that GLIDE increases non-habitual podcast streaming on Spotify home surface by up to 5.4% and new-show discovery by up to 14.3%.
• Score: 29.37272382643475
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Podcast listening is often grounded in a set of favorite shows, while listener intent can evolve over time. This combination of stable preferences and changing intent motivates recommendation approaches that support both familiarity and exploration. Traditional recommender systems typically emphasize long-term interaction patterns, and are less explicitly designed to incorporate rich contextual signals or flexible, intent-aware discovery objectives. In this setting, models that can jointly reason over semantics, context, and user state offer a promising direction. Large Language Models (LLMs) provide strong semantic reasoning and contextual conditioning for discovery-oriented recommendation, but deploying them in production introduces challenges in catalog grounding, user-level personalization, and latency-critical serving. We address these challenges with GLIDE, a production-scale generative recommender for podcast discovery at Spotify. GLIDE formulates recommendation as an instruction-following task over a discretized catalog using Semantic IDs, enabling grounded generation over a large inventory. The model conditions on recent listening history and lightweight user context, while injecting long-term user embeddings as soft prompts to capture stable preferences under strict inference constraints. We evaluate GLIDE using offline retrieval metrics, human judgments, and LLM-based evaluation, and validate its impact through large-scale online A/B testing. Across experiments involving millions of users, GLIDE increases non-habitual podcast streaming on Spotify home surface by up to 5.4% and new-show discovery by up to 14.3%, while meeting production cost and latency constraints.

Related papers

• Think2Go: Generative Next POI Recommendation with LLM Reasoning [57.37706163990998]
  Next Point-of-Interest (POI) recommendation task focuses on mining user behavioral preference patterns from historical check-ins to provide personalized suggestions for the next destination.<n>Existing methods rely on shallow contextual information and handcrafted feature interactions to predict the next POI.<n>We propose Think2Go, a novel generative next POI recommendation framework, which enhances the model's comprehension of SID representations and explores diverse spatial-temporal patterns via test-time computational scaling.
  arXiv  Detail & Related papers  (2026-07-31T03:52:20Z)
• SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation [30.06423221745951]
  We propose the Sparse Autoencoder for intent-based recommendation (SAERec)<n>SAERec automatically constructs a fine-grained and interpretable intent space from a textual corpus to guide recommendation.<n>Experiments on public demonstrate the superiority of SAERec, consistently outperforming state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-17T10:17:04Z)
• Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification [21.7465671470498]
  Referring segmentation aims to segment the target objects in images or videos based on the textual query.<n>We propose IC-Seg, a novel agentic framework that proactively clarifies user intent through multi-turn conversation.<n>We also introduce Hi-GRPO, a new hierarchical optimization strategy that injects dense and informative supervision signals at the trajectory, turn, and step levels.
  arXiv  Detail & Related papers  (2026-05-17T16:30:44Z)
• Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions [50.70965714314064]
  Large Language Models (LLMs) are increasingly serving as personal assistants, where users share complex and diverse preferences over extended interactions.<n>This work proposes RealPref, a benchmark for evaluating realistic preference-following in personalized user-LLM interactions.
  arXiv  Detail & Related papers  (2026-03-04T15:42:43Z)
• GLASS: A Generative Recommender for Long-sequence Modeling via SID-Tier and Semantic Search [51.44490997013772]
  GLASS is a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search.<n>We show that GLASS outperforms state-of-the-art baselines in experiments on two large-scale real-world datasets.
  arXiv  Detail & Related papers  (2026-02-05T13:48:33Z)
• HyMiRec: A Hybrid Multi-interest Learning Framework for LLM-based Sequential Recommendation [24.720767926024433]
  HyMiRec is a hybrid sequential recommendation framework for large language models.<n>It extracts coarse interest embeddings from long user sequences and an LLM-based recommender to captures refined interest embeddings.<n>To model the diverse preferences of users, we design a disentangled multi-interest learning module.
  arXiv  Detail & Related papers  (2025-10-15T16:45:59Z)
• Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge [8.554894195710204]
  We propose a novel framework that leverages Large Language Models (LLMs) as offline judges to assess the quality of podcast recommendations.<n>Our two-stage profile-aware approach first constructs natural-language user profiles distilled from 90 days of listening history.<n>In a controlled study with 47 participants, our profile-aware judge matched human judgments with high fidelity and outperformed or matched a variant using raw listening histories.
  arXiv  Detail & Related papers  (2025-08-12T09:23:35Z)
• Rhapsody: A Dataset for Highlight Detection in Podcasts [49.576469262265455]
  We introduce Rhapsody, a 13K podcast episodes paired with segment-level highlight.<n>We frame the podcast highlight detection as a segment-level binary classification task.<n>We explore various baseline language models and lightweight fine-tuned language models.
  arXiv  Detail & Related papers  (2025-05-26T02:39:34Z)
• Towards Explainable Temporal User Profiling with LLMs [3.719862246745416]
  We leverage large language models (LLMs) to generate natural language summaries of users' interaction histories.<n>Our framework not only models temporal user preferences but also produces natural language profiles that can be used to explain recommendations in an interpretable manner.
  arXiv  Detail & Related papers  (2025-05-01T22:02:46Z)
• Mind the Gap! Static and Interactive Evaluations of Large Audio Models [55.87220295533817]
  Large Audio Models (LAMs) are designed to power voice-native experiences.<n>This study introduces an interactive approach to evaluate LAMs and collect 7,500 LAM interactions from 484 participants.
  arXiv  Detail & Related papers  (2025-02-21T20:29:02Z)
• Latent User Intent Modeling for Sequential Recommenders [92.66888409973495]
  Sequential recommender models learn to predict the next items a user is likely to interact with based on his/her interaction history on the platform. Most sequential recommenders however lack a higher-level understanding of user intents, which often drive user behaviors online. Intent modeling is thus critical for understanding users and optimizing long-term user experience.
  arXiv  Detail & Related papers  (2022-11-17T19:00:24Z)
• Trajectory Based Podcast Recommendation [6.366468661321732]
  We show that successful and consistent recommendations can be made by viewing users as moving through the podcast library sequentially. Our approach gives a450% increase in effectiveness over a collaborative filtering baseline.
  arXiv  Detail & Related papers  (2020-09-08T16:49:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.