@inproceedings{yeh-etal-2025-leveraging,
title = "Leveraging External Knowledge Bases: Analyzing Presentation Methods and Their Impact on Model Performance",
author = "Yeh, Hui-Syuan and
Lavergne, Thomas and
Zweigenbaum, Pierre",
editor = "Ananiadou, Sophia and
Demner-Fushman, Dina and
Gupta, Deepak and
Thompson, Paul",
booktitle = "Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.cl4health-1.16/",
doi = "10.18653/v1/2025.cl4health-1.16",
pages = "193--204",
ISBN = "979-8-89176-238-1",
abstract = "Integrating external knowledge into large language models has demonstrated potential for performance improvement across a wide range of tasks. This approach is particularly appealing in domain-specific applications, such as in the biomedical field. However, the strategies for effectively presenting external knowledge to these models remain underexplored. This study investigates the impact of different knowledge presentation methods and their influence on model performance. Our results show that inserting knowledge between demonstrations helps the models perform better, and improve smaller LLMs (7B) to perform on par with larger LLMs (175B). Our further investigation indicates that the performance improvement, however, comes more from the effect of additional tokens and positioning than from the relevance of the knowledge."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yeh-etal-2025-leveraging">
<titleInfo>
<title>Leveraging External Knowledge Bases: Analyzing Presentation Methods and Their Impact on Model Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hui-Syuan</namePart>
<namePart type="family">Yeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Lavergne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health)</title>
</titleInfo>
<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">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-238-1</identifier>
</relatedItem>
<abstract>Integrating external knowledge into large language models has demonstrated potential for performance improvement across a wide range of tasks. This approach is particularly appealing in domain-specific applications, such as in the biomedical field. However, the strategies for effectively presenting external knowledge to these models remain underexplored. This study investigates the impact of different knowledge presentation methods and their influence on model performance. Our results show that inserting knowledge between demonstrations helps the models perform better, and improve smaller LLMs (7B) to perform on par with larger LLMs (175B). Our further investigation indicates that the performance improvement, however, comes more from the effect of additional tokens and positioning than from the relevance of the knowledge.</abstract>
<identifier type="citekey">yeh-etal-2025-leveraging</identifier>
<identifier type="doi">10.18653/v1/2025.cl4health-1.16</identifier>
<location>
<url>https://aclanthology.org/2025.cl4health-1.16/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>193</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging External Knowledge Bases: Analyzing Presentation Methods and Their Impact on Model Performance
%A Yeh, Hui-Syuan
%A Lavergne, Thomas
%A Zweigenbaum, Pierre
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%Y Gupta, Deepak
%Y Thompson, Paul
%S Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-238-1
%F yeh-etal-2025-leveraging
%X Integrating external knowledge into large language models has demonstrated potential for performance improvement across a wide range of tasks. This approach is particularly appealing in domain-specific applications, such as in the biomedical field. However, the strategies for effectively presenting external knowledge to these models remain underexplored. This study investigates the impact of different knowledge presentation methods and their influence on model performance. Our results show that inserting knowledge between demonstrations helps the models perform better, and improve smaller LLMs (7B) to perform on par with larger LLMs (175B). Our further investigation indicates that the performance improvement, however, comes more from the effect of additional tokens and positioning than from the relevance of the knowledge.
%R 10.18653/v1/2025.cl4health-1.16
%U https://aclanthology.org/2025.cl4health-1.16/
%U https://doi.org/10.18653/v1/2025.cl4health-1.16
%P 193-204
Markdown (Informal)
[Leveraging External Knowledge Bases: Analyzing Presentation Methods and Their Impact on Model Performance](https://aclanthology.org/2025.cl4health-1.16/) (Yeh et al., CL4Health 2025)
ACL