o-MEGA: Optimized Methods for Explanation Generation and Analysis
This work addresses the problem of model transparency and trustworthiness in NLP, particularly for misinformation detection, by providing an incremental tool to optimize explanation methods.
The paper tackles the challenge of selecting optimal explainability methods for transformer-based language models by introducing o-MEGA, a hyperparameter optimization tool that automatically identifies effective explainable AI methods and configurations, demonstrating improved transparency in automated fact-checking systems.
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.