MuChator: Enabling Active Music Discovery via Conversational Music LLMs in Douyin Music

• URL: http://arxiv.org/abs/2605.27103v1
• Date: Tue, 26 May 2026 14:42:52 GMT
• Title: MuChator: Enabling Active Music Discovery via Conversational Music LLMs in Douyin Music
• Abstract summary: We introduce MuChator, an interactive framework that enables users to actively express situational music intents in natural language.<n>MuChator incorporates three key components: Music Knowledge Pre-training, Context-aware Instruction Tuning, and Preference Alignment with Hybrid RM.<n>MuChator has been deployed on Douyin Music App within ByteDance, with 46.49% improvement of user active days in online A/B test.
• Score: 18.339515994970757
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Douyin Music, a large-scale platform with millions of daily users, adopts an immersive, feed-based discovery paradigm, where users passively explore music through continuous recommendations. While effective for passive music discovery, this paradigm restricts users to recommendation results and provides limited support for explicitly specifying listening intents. Unlike conventional search, where users express well-defined intents through explicit queries such as specific songs or artists, real-world active music discovery is often situational and colloquial, involving vague or underspecified requests. While LLMs enable natural language interaction, their direct use in music discovery remains limited by insufficient music-domain knowledge, lack of music-query collaborative reasoning, and shallow understanding of personalized preferences. To address these challenges, we introduce MuChator, an interactive MusicLLM-based framework that enables users to actively express situational music intents in natural language. MuChator incorporates three key components: (1) Music Knowledge Pre-training, a three-stage scheme that incrementally injects objective music knowledge, subjective music knowledge, and personalized music preferences into LLMs; (2) Context-aware Instruction Tuning, which constructs high-quality user-query-music triplets through an automated synthesis pipeline to align LLMs with active and situational user intents; and (3) Preference Alignment with Hybrid RM, which jointly models intent relevance, personalized preferences, and basic constraints, and is optimized using GRPO-based reinforcement learning. Extensive evaluations on industrial music recommendation datasets demonstrate that MuChator outperforms leading proprietary models, such as Gemini-3-Pro. The model has been deployed on Douyin Music App within ByteDance, with 46.49\% improvement of user active days in online A/B test.

Related papers

• FIGMA: Towards FIne-Grained Music retrievAl [65.98380295254817]
  Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.<n>We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens.<n>We propose FIGMA, a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment.
  arXiv  Detail & Related papers  (2026-06-04T18:05:39Z)
• Multimodal Music Recommendation System using LLMs [53.1178230380919]
  We propose a framework for session-based music recommendation that enriches the LastFM-1K dataset with three complementary signals.<n>We adopt the E4SRec framework by extending it with multimodal features and different item ID encoder backbones.<n>Our experiments show that integrating content-based features improves over ID-only baselines up to 95% in terms of Recall and 79% in terms of NDCG.
  arXiv  Detail & Related papers  (2026-05-28T15:34:12Z)
• Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models [54.4270504928356]
  Music Recommendation Systems (MRSs) are a cornerstone of modern streaming platforms.<n>We propose TASTE, a comprehensive dataset and benchmarking framework designed to highlight the role of multimodal information in music recommendation.<n>By leveraging recent large-scale self-supervised music encoders, we demonstrate the substantial value of the extracted audio representations across recommendation tasks.
  arXiv  Detail & Related papers  (2026-02-10T15:24:41Z)
• WeMusic-Agent: Efficient Conversational Music Recommendation via Knowledge Internalization and Agentic Boundary Learning [12.737364415781805]
  This paper proposes WeMusic-Agent, a training framework for efficient conversational music recommendation.<n>We present WeMusic-Agent-M1, an agentic model that internalizes extensive musical knowledge via continued pretraining on 50B music-related corpus.<n>We also construct a benchmark for personalized music recommendations derived from real-world data in WeChat Listen.
  arXiv  Detail & Related papers  (2025-12-18T02:59:19Z)
• Music Flamingo: Scaling Music Understanding in Audio Language Models [98.94537017112704]
  Music Flamingo is a novel large audio-language model designed to advance music understanding in foundational audio models.<n> MF-Skills is a dataset labeled through a multi-stage pipeline that yields rich captions and question-answer pairs covering harmony, structure, timbre, lyrics, and cultural context.<n>We introduce a post-training recipe: we first cold-start with MF-Think, a novel chain-of-thought dataset grounded in music theory, followed by GRPO-based reinforcement learning with custom rewards.
  arXiv  Detail & Related papers  (2025-11-13T13:21:09Z)
• Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation [47.05078668091976]
  We present JAM (Just Ask for Music), a lightweight and intuitive framework for natural language music recommendation.<n>To capture the complexity of music and user intent, JAM aggregates multimodal item features via cross-attention and sparse mixture-of-experts.<n>Our results show that JAM provides accurate recommendations, produces intuitive representations suitable for practical use cases, and can be easily integrated with existing music recommendation stacks.
  arXiv  Detail & Related papers  (2025-07-21T17:36:03Z)
• SoundSignature: What Type of Music Do You Like? [0.0]
  SoundSignature is a music application that integrates a custom OpenAI Assistant to analyze users' favorite songs. The system incorporates state-of-the-art Music Information Retrieval (MIR) Python packages to combine extracted acoustic/musical features with the assistant's extensive knowledge of the artists and bands.
  arXiv  Detail & Related papers  (2024-10-04T12:40:45Z)
• Towards Leveraging Contrastively Pretrained Neural Audio Embeddings for Recommender Tasks [18.95453617434051]
  Music recommender systems frequently utilize network-based models to capture relationships between music pieces, artists, and users. New music pieces or artists often face the cold-start problem due to insufficient initial information. To address this, one can extract content-based information directly from the music to enhance collaborative-filtering-based methods.
  arXiv  Detail & Related papers  (2024-09-13T17:53:06Z)
• LARP: Language Audio Relational Pre-training for Cold-Start Playlist Continuation [49.89372182441713]
  We introduce LARP, a multi-modal cold-start playlist continuation model. Our framework uses increasing stages of task-specific abstraction: within-track (language-audio) contrastive loss, track-track contrastive loss, and track-playlist contrastive loss.
  arXiv  Detail & Related papers  (2024-06-20T14:02:15Z)
• MusicRL: Aligning Music Generation to Human Preferences [62.44903326718772]
  MusicRL is the first music generation system finetuned from human feedback. We deploy MusicLM to users and collect a substantial dataset comprising 300,000 pairwise preferences. We train MusicRL-U, the first text-to-music model that incorporates human feedback at scale.
  arXiv  Detail & Related papers  (2024-02-06T18:36:52Z)
• MuseChat: A Conversational Music Recommendation System for Videos [12.47508840909336]
  MuseChat is a first-of-its-kind dialogue-based recommendation system that personalizes music suggestions for videos. Our system consists of two key functionalities with associated modules: recommendation and reasoning. Experiment results show that MuseChat achieves significant improvements over existing video-based music retrieval methods.
  arXiv  Detail & Related papers  (2023-10-10T03:32:33Z)
• Fairness Through Domain Awareness: Mitigating Popularity Bias For Music Discovery [56.77435520571752]
  We explore the intrinsic relationship between music discovery and popularity bias. We propose a domain-aware, individual fairness-based approach which addresses popularity bias in graph neural network (GNNs) based recommender systems. Our approach uses individual fairness to reflect a ground truth listening experience, i.e., if two songs sound similar, this similarity should be reflected in their representations.
  arXiv  Detail & Related papers  (2023-08-28T14:12:25Z)

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.