@inproceedings{cabrera-lozoya-etal-2024-optimizing,
title = "Optimizing Multimodal Large Language Models for Detection of Alcohol Advertisements via Adaptive Prompting",
author = "Cabrera Lozoya, Daniel and
Liu, Jiahe and
D{'}Alfonso, Simon and
Conway, Mike",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.42",
pages = "514--525",
abstract = "Adolescents exposed to advertisements promoting addictive substances exhibit a higher likelihood of subsequent substance use. The predominant source for youth exposure to such advertisements is through online content accessed via smartphones. Detecting these advertisements is crucial for establishing and maintaining a safer online environment for young people. In our study, we utilized Multimodal Large Language Models (MLLMs) to identify addictive substance advertisements in digital media. The performance of MLLMs depends on the quality of the prompt used to instruct the model. To optimize our prompts, an adaptive prompt engineering approach was implemented, leveraging a genetic algorithm to refine and enhance the prompts. To evaluate the model{'}s performance, we augmented the RICO dataset, consisting of Android user interface screenshots, by superimposing alcohol ads onto them. Our results indicate that the MLLM can detect advertisements promoting alcohol with a 0.94 accuracy and a 0.94 F1 score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cabrera-lozoya-etal-2024-optimizing">
<titleInfo>
<title>Optimizing Multimodal Large Language Models for Detection of Alcohol Advertisements via Adaptive Prompting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cabrera Lozoya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahe</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">D’Alfonso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Conway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Workshop on Biomedical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Adolescents exposed to advertisements promoting addictive substances exhibit a higher likelihood of subsequent substance use. The predominant source for youth exposure to such advertisements is through online content accessed via smartphones. Detecting these advertisements is crucial for establishing and maintaining a safer online environment for young people. In our study, we utilized Multimodal Large Language Models (MLLMs) to identify addictive substance advertisements in digital media. The performance of MLLMs depends on the quality of the prompt used to instruct the model. To optimize our prompts, an adaptive prompt engineering approach was implemented, leveraging a genetic algorithm to refine and enhance the prompts. To evaluate the model’s performance, we augmented the RICO dataset, consisting of Android user interface screenshots, by superimposing alcohol ads onto them. Our results indicate that the MLLM can detect advertisements promoting alcohol with a 0.94 accuracy and a 0.94 F1 score.</abstract>
<identifier type="citekey">cabrera-lozoya-etal-2024-optimizing</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.42</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>514</start>
<end>525</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Optimizing Multimodal Large Language Models for Detection of Alcohol Advertisements via Adaptive Prompting
%A Cabrera Lozoya, Daniel
%A Liu, Jiahe
%A D’Alfonso, Simon
%A Conway, Mike
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F cabrera-lozoya-etal-2024-optimizing
%X Adolescents exposed to advertisements promoting addictive substances exhibit a higher likelihood of subsequent substance use. The predominant source for youth exposure to such advertisements is through online content accessed via smartphones. Detecting these advertisements is crucial for establishing and maintaining a safer online environment for young people. In our study, we utilized Multimodal Large Language Models (MLLMs) to identify addictive substance advertisements in digital media. The performance of MLLMs depends on the quality of the prompt used to instruct the model. To optimize our prompts, an adaptive prompt engineering approach was implemented, leveraging a genetic algorithm to refine and enhance the prompts. To evaluate the model’s performance, we augmented the RICO dataset, consisting of Android user interface screenshots, by superimposing alcohol ads onto them. Our results indicate that the MLLM can detect advertisements promoting alcohol with a 0.94 accuracy and a 0.94 F1 score.
%U https://aclanthology.org/2024.bionlp-1.42
%P 514-525
Markdown (Informal)
[Optimizing Multimodal Large Language Models for Detection of Alcohol Advertisements via Adaptive Prompting](https://aclanthology.org/2024.bionlp-1.42) (Cabrera Lozoya et al., BioNLP-WS 2024)
ACL