Multimodal Music Recommendation System using LLMs

Hugging Face Daily Papers Papers

Summary

Proposes a multimodal framework integrating audio, lyric, and semantic signals with LLM-based sequential reasoning for session-based music recommendation, achieving up to 95% recall improvement over ID-only baselines.

Music recommendation systems typically treat songs as opaque tokens, relying on collaborative interaction histories which overlooks semantic or acoustic content. Prior work has explored LLM-augmented, multimodal, and text-enhanced approaches to sequential recommendation, and while some methods partially combine semantic, acoustic, or engagement signals, none jointly model all three within a unified LLM-based sequential reasoning framework that grounds recommendations in actual song content. In this work, we propose a multimodal framework for session-based music recommendation that enriches the LastFM-1K dataset with three complementary signals: (1) audio and lyric embeddings extracted using pretrained music and text representation models, (2) LLM-generated semantic metadata using the MGPHot annotation schema, and (3) listening completion ratios. We adopt the E4SRec framework by extending it with multimodal features and different item ID encoder backbones, including SASRec, BERT4Rec, and GRU4Rec. We further extend the LLM backbone option with LLaMa-2-13B, Qwen2.5-7B-Instruct, and LLaMa-3-70B in both zero-shot and fine-tuned settings. 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. Moreover, our experiments show that naive multimodal fusion does not always yield additive improvements, highlighting challenges in cross-modal integration. We release a large-scale multimodal benchmark for music recommendation.
Original Article
View Cached Full Text

Cached at: 06/05/26, 10:07 AM

Paper page - Multimodal Music Recommendation System using LLMs

Source: https://huggingface.co/papers/2606.00125

Abstract

A multimodal framework for session-based music recommendation integrates audio, lyric, and semantic signals with LLM-based sequential reasoning to improve recommendation accuracy.

Music recommendation systems typically treat songs as opaque tokens, relying on collaborative interaction histories which overlooks semantic or acoustic content. Prior work has explored LLM-augmented, multimodal, and text-enhanced approaches to sequential recommendation, and while some methods partially combine semantic, acoustic, or engagement signals, none jointly model all three within a unified LLM-based sequential reasoning framework that grounds recommendations in actual song content. In this work, we propose amultimodal frameworkfor session-based music recommendation that enriches theLastFM-1K datasetwith three complementary signals: (1) audio andlyric embeddingsextracted using pretrained music andtext representation models, (2)LLM-generated semantic metadatausing theMGPHot annotation schema, and (3)listening completion ratios. We adopt theE4SRec frameworkby extending it with multimodal features and differentitem ID encoder backbones, includingSASRec,BERT4Rec, andGRU4Rec. We further extend the LLM backbone option withLLaMa-2-13B,Qwen2.5-7B-Instruct, andLLaMa-3-70Bin both zero-shot andfine-tuned settings. Our experiments show that integrating content-based features improves over ID-only baselines up to 95% in terms ofRecalland 79% in terms ofNDCG. Moreover, our experiments show thatnaive multimodal fusiondoes not always yield additive improvements, highlighting challenges incross-modal integration. We release a large-scale multimodal benchmark for music recommendation.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2606\.00125

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.00125 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.00125 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.00125 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis

arXiv cs.CL

The paper proposes SentiLLM, a framework that uses semantic-aligned structural abstraction to distill non-verbal modalities into text-like tokens for multimodal sentiment analysis with LLMs. It introduces a dual-stream salience-context calibration mechanism and achieves superior performance on four datasets.