@inproceedings{kris-etal-2025-o,
title = "o-{MEGA}: Optimized Methods for Explanation Generation and Analysis",
author = "Kri{\v{s}}, {\v{L}}ubo{\v{s}} and
Kop{\v{c}}an, Jaroslav and
Peng, Qiwei and
Ridzik, Andrej and
Vesel{\'y}, Marcel and
Tamajka, Martin",
editor = {Habernal, Ivan and
Schulam, Peter and
Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-demos.46/",
pages = "634--642",
ISBN = "979-8-89176-334-0",
abstract = "The proliferation of transformer-based language models has revolutionized NLP domain while simultaneously introduced significant challenges regarding model transparency and trustworthiness. The complexity of achieving explainable systems in this domain is evidenced by the extensive array of explanation methods and evaluation metrics developed by researchers. To address the challenge of selecting optimal explainability approaches, we present o-mega, a hyperparameter optimization tool designed to automatically identify the most effective explainable AI methods and their configurations within the semantic matching domain. We evaluate o-mega on a post-claim matching pipeline using a curated dataset of social media posts paired with refuting claims. Our tool systematically explores different explainable methods and their hyperparameters, demonstrating improved transparency in automated fact-checking systems. As a result, such automated optimization of explanation methods can significantly enhance the interpretability of claim-matching models in critical applications such as misinformation detection, contributing to more trustworthy and transparent AI systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kris-etal-2025-o">
<titleInfo>
<title>o-MEGA: Optimized Methods for Explanation Generation and Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ľuboš</namePart>
<namePart type="family">Kriš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaroslav</namePart>
<namePart type="family">Kopčan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiwei</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrej</namePart>
<namePart type="family">Ridzik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcel</namePart>
<namePart type="family">Veselý</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Tamajka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Habernal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Schulam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-334-0</identifier>
</relatedItem>
<abstract>The proliferation of transformer-based language models has revolutionized NLP domain while simultaneously introduced significant challenges regarding model transparency and trustworthiness. The complexity of achieving explainable systems in this domain is evidenced by the extensive array of explanation methods and evaluation metrics developed by researchers. To address the challenge of selecting optimal explainability approaches, we present o-mega, a hyperparameter optimization tool designed to automatically identify the most effective explainable AI methods and their configurations within the semantic matching domain. We evaluate o-mega on a post-claim matching pipeline using a curated dataset of social media posts paired with refuting claims. Our tool systematically explores different explainable methods and their hyperparameters, demonstrating improved transparency in automated fact-checking systems. As a result, such automated optimization of explanation methods can significantly enhance the interpretability of claim-matching models in critical applications such as misinformation detection, contributing to more trustworthy and transparent AI systems.</abstract>
<identifier type="citekey">kris-etal-2025-o</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-demos.46/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>634</start>
<end>642</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T o-MEGA: Optimized Methods for Explanation Generation and Analysis
%A Kriš, Ľuboš
%A Kopčan, Jaroslav
%A Peng, Qiwei
%A Ridzik, Andrej
%A Veselý, Marcel
%A Tamajka, Martin
%Y Habernal, Ivan
%Y Schulam, Peter
%Y Tiedemann, Jörg
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-334-0
%F kris-etal-2025-o
%X The proliferation of transformer-based language models has revolutionized NLP domain while simultaneously introduced significant challenges regarding model transparency and trustworthiness. The complexity of achieving explainable systems in this domain is evidenced by the extensive array of explanation methods and evaluation metrics developed by researchers. To address the challenge of selecting optimal explainability approaches, we present o-mega, a hyperparameter optimization tool designed to automatically identify the most effective explainable AI methods and their configurations within the semantic matching domain. We evaluate o-mega on a post-claim matching pipeline using a curated dataset of social media posts paired with refuting claims. Our tool systematically explores different explainable methods and their hyperparameters, demonstrating improved transparency in automated fact-checking systems. As a result, such automated optimization of explanation methods can significantly enhance the interpretability of claim-matching models in critical applications such as misinformation detection, contributing to more trustworthy and transparent AI systems.
%U https://aclanthology.org/2025.emnlp-demos.46/
%P 634-642
Markdown (Informal)
[o-MEGA: Optimized Methods for Explanation Generation and Analysis](https://aclanthology.org/2025.emnlp-demos.46/) (Kriš et al., EMNLP 2025)
ACL
- Ľuboš Kriš, Jaroslav Kopčan, Qiwei Peng, Andrej Ridzik, Marcel Veselý, and Martin Tamajka. 2025. o-MEGA: Optimized Methods for Explanation Generation and Analysis. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 634–642, Suzhou, China. Association for Computational Linguistics.