@inproceedings{salvi-etal-2025-towards,
title = "Towards Understanding {LLM}-Generated Biomedical Lay Summaries",
author = "Salvi, Rohan Charudatt and
Panigrahi, Swapnil and
Jain, Dhruv and
Yadav, Shweta and
Akhtar, Md. Shad",
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-1.22/",
doi = "10.18653/v1/2025.cl4health-1.22",
pages = "260--268",
ISBN = "979-8-89176-238-1",
abstract = "In this paper, we investigate using large language models to generate accessible lay summaries of medical abstracts, targeting non-expert audiences. We assess the ability of models like GPT-4 and LLaMA 3-8B-Instruct to simplify complex medical information, focusing on layness, comprehensiveness, and factual accuracy. Utilizing both automated and human evaluations, we discover that automatic metrics do not always align with human judgments. Our analysis highlights the potential benefits of developing clear guidelines for consistent evaluations conducted by non-expert reviewers. It also points to areas for improvement in the evaluation process and the creation of lay summaries for future research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salvi-etal-2025-towards">
<titleInfo>
<title>Towards Understanding LLM-Generated Biomedical Lay Summaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rohan</namePart>
<namePart type="given">Charudatt</namePart>
<namePart type="family">Salvi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swapnil</namePart>
<namePart type="family">Panigrahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhruv</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shweta</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</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>In this paper, we investigate using large language models to generate accessible lay summaries of medical abstracts, targeting non-expert audiences. We assess the ability of models like GPT-4 and LLaMA 3-8B-Instruct to simplify complex medical information, focusing on layness, comprehensiveness, and factual accuracy. Utilizing both automated and human evaluations, we discover that automatic metrics do not always align with human judgments. Our analysis highlights the potential benefits of developing clear guidelines for consistent evaluations conducted by non-expert reviewers. It also points to areas for improvement in the evaluation process and the creation of lay summaries for future research.</abstract>
<identifier type="citekey">salvi-etal-2025-towards</identifier>
<identifier type="doi">10.18653/v1/2025.cl4health-1.22</identifier>
<location>
<url>https://aclanthology.org/2025.cl4health-1.22/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>260</start>
<end>268</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Understanding LLM-Generated Biomedical Lay Summaries
%A Salvi, Rohan Charudatt
%A Panigrahi, Swapnil
%A Jain, Dhruv
%A Yadav, Shweta
%A Akhtar, Md. Shad
%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 salvi-etal-2025-towards
%X In this paper, we investigate using large language models to generate accessible lay summaries of medical abstracts, targeting non-expert audiences. We assess the ability of models like GPT-4 and LLaMA 3-8B-Instruct to simplify complex medical information, focusing on layness, comprehensiveness, and factual accuracy. Utilizing both automated and human evaluations, we discover that automatic metrics do not always align with human judgments. Our analysis highlights the potential benefits of developing clear guidelines for consistent evaluations conducted by non-expert reviewers. It also points to areas for improvement in the evaluation process and the creation of lay summaries for future research.
%R 10.18653/v1/2025.cl4health-1.22
%U https://aclanthology.org/2025.cl4health-1.22/
%U https://doi.org/10.18653/v1/2025.cl4health-1.22
%P 260-268
Markdown (Informal)
[Towards Understanding LLM-Generated Biomedical Lay Summaries](https://aclanthology.org/2025.cl4health-1.22/) (Salvi et al., CL4Health 2025)
ACL
- Rohan Charudatt Salvi, Swapnil Panigrahi, Dhruv Jain, Shweta Yadav, and Md. Shad Akhtar. 2025. Towards Understanding LLM-Generated Biomedical Lay Summaries. In Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health), pages 260–268, Albuquerque, New Mexico. Association for Computational Linguistics.