@inproceedings{kruspe-2024-musical,
title = "Musical Ethnocentrism in Large Language Models",
author = "Kruspe, Anna",
editor = "Kruspe, Anna and
Oramas, Sergio and
Epure, Elena V. and
Sordo, Mohamed and
Weck, Benno and
Doh, SeungHeon and
Won, Minz and
Manco, Ilaria and
Meseguer-Brocal, Gabriel",
booktitle = "Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA)",
month = nov,
year = "2024",
address = "Oakland, USA",
publisher = "Association for Computational Lingustics",
url = "https://aclanthology.org/2024.nlp4musa-1.11/",
pages = "62--68",
abstract = "Large Language Models (LLMs) reflect the biases in their training data and, by extension, those of the people who created this training data. Detecting, analyzing, and mitigating such biases is becoming a focus of research. One type of bias that has been understudied so far are geocultural biases. Those can be caused by an imbalance in the representation of different geographic regions and cultures in the training data, but also by value judgments contained therein. In this paper, we make a first step towards analyzing musical biases in LLMs, particularly ChatGPT and Mixtral. We conduct two experiments. In the first, we prompt LLMs to provide lists of the {\textquotedblleft}Top 100{\textquotedblright} musical contributors of various categories and analyze their countries of origin. In the second experiment, we ask the LLMs to numerically rate various aspects of the musical cultures of different countries. Our results indicate a strong preference of the LLMs for Western music cultures in both experiments."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kruspe-2024-musical">
<titleInfo>
<title>Musical Ethnocentrism in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kruspe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kruspe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="family">Oramas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Epure</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Sordo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benno</namePart>
<namePart type="family">Weck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SeungHeon</namePart>
<namePart type="family">Doh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minz</namePart>
<namePart type="family">Won</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilaria</namePart>
<namePart type="family">Manco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Meseguer-Brocal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Lingustics</publisher>
<place>
<placeTerm type="text">Oakland, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) reflect the biases in their training data and, by extension, those of the people who created this training data. Detecting, analyzing, and mitigating such biases is becoming a focus of research. One type of bias that has been understudied so far are geocultural biases. Those can be caused by an imbalance in the representation of different geographic regions and cultures in the training data, but also by value judgments contained therein. In this paper, we make a first step towards analyzing musical biases in LLMs, particularly ChatGPT and Mixtral. We conduct two experiments. In the first, we prompt LLMs to provide lists of the “Top 100” musical contributors of various categories and analyze their countries of origin. In the second experiment, we ask the LLMs to numerically rate various aspects of the musical cultures of different countries. Our results indicate a strong preference of the LLMs for Western music cultures in both experiments.</abstract>
<identifier type="citekey">kruspe-2024-musical</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4musa-1.11/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>62</start>
<end>68</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Musical Ethnocentrism in Large Language Models
%A Kruspe, Anna
%Y Kruspe, Anna
%Y Oramas, Sergio
%Y Epure, Elena V.
%Y Sordo, Mohamed
%Y Weck, Benno
%Y Doh, SeungHeon
%Y Won, Minz
%Y Manco, Ilaria
%Y Meseguer-Brocal, Gabriel
%S Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA)
%D 2024
%8 November
%I Association for Computational Lingustics
%C Oakland, USA
%F kruspe-2024-musical
%X Large Language Models (LLMs) reflect the biases in their training data and, by extension, those of the people who created this training data. Detecting, analyzing, and mitigating such biases is becoming a focus of research. One type of bias that has been understudied so far are geocultural biases. Those can be caused by an imbalance in the representation of different geographic regions and cultures in the training data, but also by value judgments contained therein. In this paper, we make a first step towards analyzing musical biases in LLMs, particularly ChatGPT and Mixtral. We conduct two experiments. In the first, we prompt LLMs to provide lists of the “Top 100” musical contributors of various categories and analyze their countries of origin. In the second experiment, we ask the LLMs to numerically rate various aspects of the musical cultures of different countries. Our results indicate a strong preference of the LLMs for Western music cultures in both experiments.
%U https://aclanthology.org/2024.nlp4musa-1.11/
%P 62-68
Markdown (Informal)
[Musical Ethnocentrism in Large Language Models](https://aclanthology.org/2024.nlp4musa-1.11/) (Kruspe, NLP4MusA 2024)
ACL