# Generating Symbolic Music from Natural Language Prompts using an LLM-Enhanced Dataset

arXiv: https://arxiv.org/abs/2410.02084 · HTML: https://mlsanity.com/paper/2410.02084/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2024.

## Built on by (most cited first, 9 of 9)

- [WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning](https://mlsanity.com/paper/2509.04744/) (2025)
- [LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR](https://mlsanity.com/paper/2506.19065/) (2025)
- [SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton](https://mlsanity.com/paper/2604.25498/) (2026)
- [MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding](https://mlsanity.com/paper/2510.16273/) (2025)
- [How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation](https://mlsanity.com/paper/2601.22764/) (2026)
- [Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training](https://mlsanity.com/paper/2605.10835/) (2026)
- [MusPyExpress: Extending MusPy with Enhanced Expression Text Support](https://mlsanity.com/paper/2608.21678/) (2026)
- [Mode-conditioned music learning and composition: a spiking neural network inspired by neuroscience and psychology](https://mlsanity.com/paper/2411.14773/) (2024)
- [Libretto: Giving LLM Agents a Sense of Musical Structure](https://mlsanity.com/paper/2606.22708/) (2026)

## Abstract (arXiv)

Recent years have seen many audio-domain text-to-music generation models that rely on large amounts of text-audio pairs for training. However, symbolic-domain controllable music generation has lagged behind partly due to the lack of a large-scale symbolic music dataset with extensive metadata and captions. In this work, we present MetaScore, a new dataset consisting of 963K musical scores paired with rich metadata, including free-form user-annotated tags, collected from an online music forum. To approach text-to-music generation, We employ a pretrained large language model (LLM) to generate pseudo-natural language captions for music from its metadata tags. With the LLM-enhanced MetaScore, we train a text-conditioned music generation model that learns to generate symbolic music from the pseudo captions, allowing control of instruments, genre, composer, complexity and other free-form music descriptors. In addition, we train a tag-conditioned system that supports a predefined set of tags available in MetaScore. Our experimental results show that both the proposed text-to-music and tags-to-music models outperform a baseline text-to-music model in a listening test. While a concurrent work Text2MIDI also supports free-form text input, our models achieve comparable performance. Moreover, the text-to-music system offers a more natural interface than the tags-to-music model, as it allows users to provide free-form natural language prompts.