# Towards the Generation of Musical Explanations with GPT-3

arXiv: https://arxiv.org/abs/2206.08264 · HTML: https://mlsanity.com/paper/2206.08264/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 11 May 2022.

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [In a Silent Way: Communication Between AI and Improvising Musicians Beyond Sound](https://mlsanity.com/paper/1902.06442/) (2019)
- [Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings](https://mlsanity.com/paper/2109.07833/) (2021)
- [Explainable PCGML via Game Design Patterns](https://mlsanity.com/paper/1809.09419/) (2018)
- [Composer Style Classification of Piano Sheet Music Images Using Language Model Pretraining](https://mlsanity.com/paper/2007.14587/) (2020)
- [Transformer-based approach towards music emotion recognition from lyrics](https://mlsanity.com/paper/2101.02051/) (2021)
- [Moving to Communicate, Moving to Interact: Patterns of Body Motion in Musical Duo Performance](https://mlsanity.com/paper/1911.09018/) (2019)
- [Musical Speech: A Transformer-based Composition Tool](https://mlsanity.com/paper/2108.01043/) (2021)

## Built on by (most cited first, 1 of 1)

- [Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey](https://mlsanity.com/paper/2402.17467/) (2024)

## Abstract (arXiv)

Open AI's language model, GPT-3, has shown great potential for many NLP tasks, with applications in many different domains. In this work we carry out a first study on GPT-3's capability to communicate musical decisions through textual explanations when prompted with a textual representation of a piece of music. Enabling a dialogue in human-AI music partnerships is an important step towards more engaging and creative human-AI interactions. Our results show that GPT-3 lacks the necessary intelligence to really understand musical decisions. A major barrier to reach a better performance is the lack of data that includes explanations of the creative process carried out by artists for musical pieces. We believe such a resource would aid the understanding and collaboration with AI music systems.