Saved in:
Bibliographic Details
Main Authors: Kriš, Ľuboš, Kopčan, Jaroslav, Peng, Qiwei, Ridzik, Andrej, Veselý, Marcel, Tamajka, Martin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.00288
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916981927575552
author Kriš, Ľuboš
Kopčan, Jaroslav
Peng, Qiwei
Ridzik, Andrej
Veselý, Marcel
Tamajka, Martin
author_facet Kriš, Ľuboš
Kopčan, Jaroslav
Peng, Qiwei
Ridzik, Andrej
Veselý, Marcel
Tamajka, Martin
contents 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 \textbf{\texttt{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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00288
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle o-MEGA: Optimized Methods for Explanation Generation and Analysis
Kriš, Ľuboš
Kopčan, Jaroslav
Peng, Qiwei
Ridzik, Andrej
Veselý, Marcel
Tamajka, Martin
Computation and Language
Artificial Intelligence
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 \textbf{\texttt{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.
title o-MEGA: Optimized Methods for Explanation Generation and Analysis
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.00288