@inproceedings{de-la-iglesia-etal-2025-ranking,
title = "Ranking Over Scoring: Towards Reliable and Robust Automated Evaluation of {LLM}-Generated Medical Explanatory Arguments",
author = "De la Iglesia, Iker and
Goenaga, Iakes and
Ramirez-Romero, Johanna and
Villa-Gonzalez, Jose Maria and
Goikoetxea, Josu and
Barrena, Ander",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.634/",
pages = "9456--9471",
abstract = "Evaluating LLM-generated text has become a key challenge, especially in domain-specific contexts like the medical field. This work introduces a novel evaluation methodology for LLM-generated medical explanatory arguments, relying on Proxy Tasks and rankings to closely align results with human evaluation criteria, overcoming the biases typically seen in LLMs used as judges. We demonstrate that the proposed evaluators are robust against adversarial attacks, including the assessment of non-argumentative text. Additionally, the human-crafted arguments needed to train the evaluators are minimized to just one example per Proxy Task. By examining multiple LLM-generated arguments, we establish a methodology for determining whether a Proxy Task is suitable for evaluating LLM-generated medical explanatory arguments, requiring only five examples and two human experts."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-la-iglesia-etal-2025-ranking">
<titleInfo>
<title>Ranking Over Scoring: Towards Reliable and Robust Automated Evaluation of LLM-Generated Medical Explanatory Arguments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iker</namePart>
<namePart type="family">De la Iglesia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iakes</namePart>
<namePart type="family">Goenaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Ramirez-Romero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Villa-Gonzalez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josu</namePart>
<namePart type="family">Goikoetxea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ander</namePart>
<namePart type="family">Barrena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Evaluating LLM-generated text has become a key challenge, especially in domain-specific contexts like the medical field. This work introduces a novel evaluation methodology for LLM-generated medical explanatory arguments, relying on Proxy Tasks and rankings to closely align results with human evaluation criteria, overcoming the biases typically seen in LLMs used as judges. We demonstrate that the proposed evaluators are robust against adversarial attacks, including the assessment of non-argumentative text. Additionally, the human-crafted arguments needed to train the evaluators are minimized to just one example per Proxy Task. By examining multiple LLM-generated arguments, we establish a methodology for determining whether a Proxy Task is suitable for evaluating LLM-generated medical explanatory arguments, requiring only five examples and two human experts.</abstract>
<identifier type="citekey">de-la-iglesia-etal-2025-ranking</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.634/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>9456</start>
<end>9471</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ranking Over Scoring: Towards Reliable and Robust Automated Evaluation of LLM-Generated Medical Explanatory Arguments
%A De la Iglesia, Iker
%A Goenaga, Iakes
%A Ramirez-Romero, Johanna
%A Villa-Gonzalez, Jose Maria
%A Goikoetxea, Josu
%A Barrena, Ander
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F de-la-iglesia-etal-2025-ranking
%X Evaluating LLM-generated text has become a key challenge, especially in domain-specific contexts like the medical field. This work introduces a novel evaluation methodology for LLM-generated medical explanatory arguments, relying on Proxy Tasks and rankings to closely align results with human evaluation criteria, overcoming the biases typically seen in LLMs used as judges. We demonstrate that the proposed evaluators are robust against adversarial attacks, including the assessment of non-argumentative text. Additionally, the human-crafted arguments needed to train the evaluators are minimized to just one example per Proxy Task. By examining multiple LLM-generated arguments, we establish a methodology for determining whether a Proxy Task is suitable for evaluating LLM-generated medical explanatory arguments, requiring only five examples and two human experts.
%U https://aclanthology.org/2025.coling-main.634/
%P 9456-9471
Markdown (Informal)
[Ranking Over Scoring: Towards Reliable and Robust Automated Evaluation of LLM-Generated Medical Explanatory Arguments](https://aclanthology.org/2025.coling-main.634/) (De la Iglesia et al., COLING 2025)
ACL