@inproceedings{to-etal-2024-deakinnlp,
title = "{D}eakin{NLP} at {B}io{L}ay{S}umm: Evaluating Fine-tuning Longformer and {GPT}-4 Prompting for Biomedical Lay Summarization",
author = "To, Huy Quoc and
Liu, Ming and
Huang, Guangyan",
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-1.67",
doi = "10.18653/v1/2024.bionlp-1.67",
pages = "748--754",
abstract = "This paper presents our approaches for the BioLaySumm 2024 Shared Task. We evaluate two methods for generating lay summaries based on biomedical articles: (1) fine-tuning the Longformer-Encoder-Decoder (LED) model, and (2) zero-shot and few-shot prompting on GPT-4. In the fine-tuning approach, we individually fine-tune the LED model using two datasets: PLOS and eLife. This process is conducted under two different settings: one utilizing 50{\%} of the training dataset, and the other utilizing the entire 100{\%} of the training dataset. We compare the results of both methods with GPT-4 in zero-shot and few-shot prompting. The experiment results demonstrate that fine-tuning with 100{\%} of the training data achieves better performance than prompting with GPT-4. However, under data scarcity circumstances, prompting GPT-4 seems to be a better solution.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="to-etal-2024-deakinnlp">
<titleInfo>
<title>DeakinNLP at BioLaySumm: Evaluating Fine-tuning Longformer and GPT-4 Prompting for Biomedical Lay Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huy</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">To</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangyan</namePart>
<namePart type="family">Huang</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>This paper presents our approaches for the BioLaySumm 2024 Shared Task. We evaluate two methods for generating lay summaries based on biomedical articles: (1) fine-tuning the Longformer-Encoder-Decoder (LED) model, and (2) zero-shot and few-shot prompting on GPT-4. In the fine-tuning approach, we individually fine-tune the LED model using two datasets: PLOS and eLife. This process is conducted under two different settings: one utilizing 50% of the training dataset, and the other utilizing the entire 100% of the training dataset. We compare the results of both methods with GPT-4 in zero-shot and few-shot prompting. The experiment results demonstrate that fine-tuning with 100% of the training data achieves better performance than prompting with GPT-4. However, under data scarcity circumstances, prompting GPT-4 seems to be a better solution.</abstract>
<identifier type="citekey">to-etal-2024-deakinnlp</identifier>
<identifier type="doi">10.18653/v1/2024.bionlp-1.67</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.67</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>748</start>
<end>754</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeakinNLP at BioLaySumm: Evaluating Fine-tuning Longformer and GPT-4 Prompting for Biomedical Lay Summarization
%A To, Huy Quoc
%A Liu, Ming
%A Huang, Guangyan
%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 to-etal-2024-deakinnlp
%X This paper presents our approaches for the BioLaySumm 2024 Shared Task. We evaluate two methods for generating lay summaries based on biomedical articles: (1) fine-tuning the Longformer-Encoder-Decoder (LED) model, and (2) zero-shot and few-shot prompting on GPT-4. In the fine-tuning approach, we individually fine-tune the LED model using two datasets: PLOS and eLife. This process is conducted under two different settings: one utilizing 50% of the training dataset, and the other utilizing the entire 100% of the training dataset. We compare the results of both methods with GPT-4 in zero-shot and few-shot prompting. The experiment results demonstrate that fine-tuning with 100% of the training data achieves better performance than prompting with GPT-4. However, under data scarcity circumstances, prompting GPT-4 seems to be a better solution.
%R 10.18653/v1/2024.bionlp-1.67
%U https://aclanthology.org/2024.bionlp-1.67
%U https://doi.org/10.18653/v1/2024.bionlp-1.67
%P 748-754
Markdown (Informal)
[DeakinNLP at BioLaySumm: Evaluating Fine-tuning Longformer and GPT-4 Prompting for Biomedical Lay Summarization](https://aclanthology.org/2024.bionlp-1.67) (To et al., BioNLP-WS 2024)
ACL