@inproceedings{hachmeier-jaschke-2025-benchmark,
title = "A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection",
author = {Hachmeier, Simon and
J{\"a}schke, Robert},
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.658/",
pages = "9845--9859",
abstract = "Detecting music entities such as song titles or artist names is a useful application to help use cases like processing music search queries or analyzing music consumption on the web. Recent approaches incorporate smaller language models (SLMs) like BERT and achieve high results. However, further research indicates a high influence of entity exposure during pre-training on the performance of the models. With the advent of large language models (LLMs), these outperform SLMs in a variety of downstream tasks. However, researchers are still divided if this is applicable to tasks like entity detection in texts due to issues like hallucination. In this paper, we provide a novel dataset of user-generated metadata and conduct a benchmark and a robustness study using recent LLMs with in-context-learning (ICL). Our results indicate that LLMs in the ICL setting yield higher performance than SLMs. We further uncover the large impact of entity exposure on the best performing LLM in our study."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hachmeier-jaschke-2025-benchmark">
<titleInfo>
<title>A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Hachmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Jäschke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Detecting music entities such as song titles or artist names is a useful application to help use cases like processing music search queries or analyzing music consumption on the web. Recent approaches incorporate smaller language models (SLMs) like BERT and achieve high results. However, further research indicates a high influence of entity exposure during pre-training on the performance of the models. With the advent of large language models (LLMs), these outperform SLMs in a variety of downstream tasks. However, researchers are still divided if this is applicable to tasks like entity detection in texts due to issues like hallucination. In this paper, we provide a novel dataset of user-generated metadata and conduct a benchmark and a robustness study using recent LLMs with in-context-learning (ICL). Our results indicate that LLMs in the ICL setting yield higher performance than SLMs. We further uncover the large impact of entity exposure on the best performing LLM in our study.</abstract>
<identifier type="citekey">hachmeier-jaschke-2025-benchmark</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.658/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>9845</start>
<end>9859</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection
%A Hachmeier, Simon
%A Jäschke, Robert
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F hachmeier-jaschke-2025-benchmark
%X Detecting music entities such as song titles or artist names is a useful application to help use cases like processing music search queries or analyzing music consumption on the web. Recent approaches incorporate smaller language models (SLMs) like BERT and achieve high results. However, further research indicates a high influence of entity exposure during pre-training on the performance of the models. With the advent of large language models (LLMs), these outperform SLMs in a variety of downstream tasks. However, researchers are still divided if this is applicable to tasks like entity detection in texts due to issues like hallucination. In this paper, we provide a novel dataset of user-generated metadata and conduct a benchmark and a robustness study using recent LLMs with in-context-learning (ICL). Our results indicate that LLMs in the ICL setting yield higher performance than SLMs. We further uncover the large impact of entity exposure on the best performing LLM in our study.
%U https://aclanthology.org/2025.coling-main.658/
%P 9845-9859
Markdown (Informal)
[A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection](https://aclanthology.org/2025.coling-main.658/) (Hachmeier & Jäschke, COLING 2025)
ACL