@inproceedings{menchaca-resendiz-etal-2025-supporting,
title = "Supporting Plain Language Summarization of Psychological Meta-Analyses with Large Language Models",
author = "Menchaca Resendiz, Yarik and
Kerwer, Martin and
Chasiotis, Anita and
Bodemer, Marlene and
Sassenberg, Kai and
Klinger, Roman",
editor = "Liu, Xuebo and
Purwarianti, Ayu",
booktitle = "Proceedings of The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-demo.4/",
pages = "25--35",
ISBN = "979-8-89176-301-2",
abstract = "Communicating complex scientific findings to non-experts remains a major challenge in fields like psychology, where research is often presented in highly technical language. One effective way to improve accessibility, for non-experts, is through plain language summaries, which summarize key insights into simple and understandable terms. However, the limited number of institutions that produce lay summaries typically relies on psychology experts to create them manually {--} an approach that ensures high quality but requires significant expertise, time, and effort. In this paper, we introduce the KLARpsy App, a system designed to support psychology experts in creating plain language summaries of psychological meta-analyses using Large Language Models (LLM). Our system generates initial draft summaries based on a 37-criterion guideline developed to ensure clarity for non-experts. All summaries produced through the system are manually validated and edited by KLARpsy authors to ensure factual correctness and readability. We demonstrate how the system integrates LLM-generated content into an expert-in-the-loop workflow. The automatic evaluation showed a mean semantic-similarity score of 0.73 against expert-written summaries, and human evaluation on a 5-point Likert scale averaged above 3 (higher is better), indicate that the generated drafts are of high quality. The application and code are open source."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="menchaca-resendiz-etal-2025-supporting">
<titleInfo>
<title>Supporting Plain Language Summarization of Psychological Meta-Analyses with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yarik</namePart>
<namePart type="family">Menchaca Resendiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Kerwer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">Chasiotis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marlene</namePart>
<namePart type="family">Bodemer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Sassenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuebo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-301-2</identifier>
</relatedItem>
<abstract>Communicating complex scientific findings to non-experts remains a major challenge in fields like psychology, where research is often presented in highly technical language. One effective way to improve accessibility, for non-experts, is through plain language summaries, which summarize key insights into simple and understandable terms. However, the limited number of institutions that produce lay summaries typically relies on psychology experts to create them manually – an approach that ensures high quality but requires significant expertise, time, and effort. In this paper, we introduce the KLARpsy App, a system designed to support psychology experts in creating plain language summaries of psychological meta-analyses using Large Language Models (LLM). Our system generates initial draft summaries based on a 37-criterion guideline developed to ensure clarity for non-experts. All summaries produced through the system are manually validated and edited by KLARpsy authors to ensure factual correctness and readability. We demonstrate how the system integrates LLM-generated content into an expert-in-the-loop workflow. The automatic evaluation showed a mean semantic-similarity score of 0.73 against expert-written summaries, and human evaluation on a 5-point Likert scale averaged above 3 (higher is better), indicate that the generated drafts are of high quality. The application and code are open source.</abstract>
<identifier type="citekey">menchaca-resendiz-etal-2025-supporting</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-demo.4/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>25</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Supporting Plain Language Summarization of Psychological Meta-Analyses with Large Language Models
%A Menchaca Resendiz, Yarik
%A Kerwer, Martin
%A Chasiotis, Anita
%A Bodemer, Marlene
%A Sassenberg, Kai
%A Klinger, Roman
%Y Liu, Xuebo
%Y Purwarianti, Ayu
%S Proceedings of The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-301-2
%F menchaca-resendiz-etal-2025-supporting
%X Communicating complex scientific findings to non-experts remains a major challenge in fields like psychology, where research is often presented in highly technical language. One effective way to improve accessibility, for non-experts, is through plain language summaries, which summarize key insights into simple and understandable terms. However, the limited number of institutions that produce lay summaries typically relies on psychology experts to create them manually – an approach that ensures high quality but requires significant expertise, time, and effort. In this paper, we introduce the KLARpsy App, a system designed to support psychology experts in creating plain language summaries of psychological meta-analyses using Large Language Models (LLM). Our system generates initial draft summaries based on a 37-criterion guideline developed to ensure clarity for non-experts. All summaries produced through the system are manually validated and edited by KLARpsy authors to ensure factual correctness and readability. We demonstrate how the system integrates LLM-generated content into an expert-in-the-loop workflow. The automatic evaluation showed a mean semantic-similarity score of 0.73 against expert-written summaries, and human evaluation on a 5-point Likert scale averaged above 3 (higher is better), indicate that the generated drafts are of high quality. The application and code are open source.
%U https://aclanthology.org/2025.ijcnlp-demo.4/
%P 25-35
Markdown (Informal)
[Supporting Plain Language Summarization of Psychological Meta-Analyses with Large Language Models](https://aclanthology.org/2025.ijcnlp-demo.4/) (Menchaca Resendiz et al., IJCNLP 2025)
ACL
- Yarik Menchaca Resendiz, Martin Kerwer, Anita Chasiotis, Marlene Bodemer, Kai Sassenberg, and Roman Klinger. 2025. Supporting Plain Language Summarization of Psychological Meta-Analyses with Large Language Models. In Proceedings of The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations, pages 25–35, Mumbai, India. Association for Computational Linguistics.