# Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning

arXiv: https://arxiv.org/abs/2308.11276 · HTML: https://mlsanity.com/paper/2308.11276/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 22 Aug 2023.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Listen, Think, and Understand](https://mlsanity.com/paper/2305.10790/) (2023)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [LP-MusicCaps: LLM-Based Pseudo Music Captioning](https://mlsanity.com/paper/2307.16372/) (2023)
- [Mousai: Text-to-Music Generation with Long-Context Latent Diffusion](https://mlsanity.com/paper/2301.11757/) (2023)
- [Codified audio language modeling learns useful representations for music information retrieval](https://mlsanity.com/paper/2107.05677/) (2021)
- [Audio Captioning Transformer](https://mlsanity.com/paper/2107.09817/) (2021)
- [UnIVAL: Unified Model for Image, Video, Audio and Language Tasks](https://mlsanity.com/paper/2307.16184/) (2023)
- [MusCaps: Generating Captions for Music Audio](https://mlsanity.com/paper/2104.11984/) (2021)
- [Robust Vector Quantized-Variational Autoencoder](https://mlsanity.com/paper/2202.01987/) (2022)

## Built on by (most cited first, 30 of 77)

- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2410.19168/) (2024)
- [Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities](https://mlsanity.com/paper/2402.01831/) (2024)
- [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025)
- [MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix](https://mlsanity.com/paper/2505.13032/) (2025)
- [Large Language Models for Time Series: A Survey](https://mlsanity.com/paper/2402.01801/) (2024)
- [OmniBench: Towards The Future of Universal Omni-Language Models](https://mlsanity.com/paper/2409.15272/) (2024)
- [Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://mlsanity.com/paper/2503.02318/) (2025)
- [Connecting Speech Encoder and Large Language Model for ASR](https://mlsanity.com/paper/2309.13963/) (2023)
- [The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation](https://mlsanity.com/paper/2311.10057/) (2023)
- [MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response](https://mlsanity.com/paper/2309.08730/) (2023)
- [MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models](https://mlsanity.com/paper/2408.01337/) (2024)
- [Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching](https://mlsanity.com/paper/2311.12751/) (2023)
- [Foundation Models for Music: A Survey](https://mlsanity.com/paper/2408.14340/) (2024)
- [DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment](https://mlsanity.com/paper/2406.18871/) (2024)
- [MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models](https://mlsanity.com/paper/2402.06178/) (2024)
- [Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models](https://mlsanity.com/paper/2406.08402/) (2024)
- [Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning](https://mlsanity.com/paper/2410.16130/) (2024)
- [LLark: A Multimodal Instruction-Following Language Model for Music](https://mlsanity.com/paper/2310.07160/) (2023)
- [InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue](https://mlsanity.com/paper/2510.13747/) (2025)
- [MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh](https://mlsanity.com/paper/2508.01242/) (2025)
- [UniMuMo: Unified Text, Music and Motion Generation](https://mlsanity.com/paper/2410.04534/) (2024)
- [Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music](https://mlsanity.com/paper/2604.10905/) (2026)
- [CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following](https://mlsanity.com/paper/2506.12285/) (2025)
- [The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2406.15885/) (2024)
- [OpenMU: Your Swiss Army Knife for Music Understanding](https://mlsanity.com/paper/2410.15573/) (2024)
- [DIFFA: Large Language Diffusion Models Can Listen and Understand](https://mlsanity.com/paper/2507.18452/) (2025)
- [Audio Dialogues: Dialogues dataset for audio and music understanding](https://mlsanity.com/paper/2404.07616/) (2024)
- [Quality-aware Masked Diffusion Transformer for Enhanced Music Generation](https://mlsanity.com/paper/2405.15863/) (2024)
- [ABC-Eval: Benchmarking Large Language Models on Symbolic Music Understanding and Instruction Following](https://mlsanity.com/paper/2509.23350/) (2025)

## Abstract (arXiv)

Text-to-music generation (T2M-Gen) faces a major obstacle due to the scarcity of large-scale publicly available music datasets with natural language captions. To address this, we propose the Music Understanding LLaMA (MU-LLaMA), capable of answering music-related questions and generating captions for music files. Our model utilizes audio representations from a pretrained MERT model to extract music features. However, obtaining a suitable dataset for training the MU-LLaMA model remains challenging, as existing publicly accessible audio question answering datasets lack the necessary depth for open-ended music question answering. To fill this gap, we present a methodology for generating question-answer pairs from existing audio captioning datasets and introduce the MusicQA Dataset designed for answering open-ended music-related questions. The experiments demonstrate that the proposed MU-LLaMA model, trained on our designed MusicQA dataset, achieves outstanding performance in both music question answering and music caption generation across various metrics, outperforming current state-of-the-art (SOTA) models in both fields and offering a promising advancement in the T2M-Gen research field.