International Conference on Information and Knowledge Technology

فارسی

Home / شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

A Framework for Systematic Stability Assessment of Post-hoc Explanations in Text Classification

Authors :

Parman Mohammadalizadeh¹ Parham Mohammadalizadeh² Ayda Mahmoudian³

1- دانشگاه زنجان 2- پژوهشگر مستقل 3- پژوهشگر مستقل

Keywords :

Explainable AI،Explainability Evaluation،Natural Language Processing

Abstract :

Post-hoc explanation methods are widely adopted for interpreting neural text classifiers, yet lack standardized evaluation of their stability under input perturbations. We present a systematic framework for assessing explanation stability through three categories of stress tests: preprocessing variations, semantic paraphrasing, and explainer seed variations. The framework combines quantitative metrics (Jaccard similarity, Spearman correlation, attribution differences) with automated stability card generation for standardized reporting. We evaluate Integrated Gradients, LIME, and SHAP across four model-dataset combinations spanning sentiment analysis and topic classification. Results reveal nuanced stability patterns, including the decoupling of model capacity from explanation reliability and architecture-dependent vulnerability to perturbation types. Our open-source implementation supports standard transformer models and explanation libraries, establishing practical stability assessment as a reproducible evaluation standard for NLP explainability research.

List of archived papers

انتخاب ویژگی با استفاده از الگوریتم بهینه سازی ذرات مبتنی بر استراتژی خود تطبیقی دودویی جهت تشخیص بیماری

الهام صالحی - دکتر محمدرضا کرمی ملایی - دکتر حسام عمرانپور الهام صالحی - محمدرضا کرمی ملایی - حسام عمرانپور -

A Hybrid Crow Search and Penguin Optimization Algorithm (CPMM) for Efficient Cloud Workflow Scheduling

Reza Akraminejad - Farhad Kazemipour - Mozhdeh Koreh Davoodi

Fast Online Character Recognition Using a Novel Local-Global Feature Extraction Method

Ayoub Parvizi - Dr Mohammad Kazemifard - Ziba Imani

Presentation of a New Decoder Based on Quantum Cellular Automata Technology Along with an Analysis of Energy Consumption

- - -

جایگذاری مقادیر ازدست رفته در داده های سری زمانی چندمتغیره برای پیش بینی مرگ ومیر بیماران با رویکرد یادگیری عمیق مبتنی بر مکانیسم توجه

سید علی هاشمی - سعید جلیلی

Enhancing QSAR Modeling: A Fusion of Sequential Feature Selection and Support Vector Machine

Farzaneh Khajehgili-Mirabadi - Mohammad Reza Keyvanpour

A Comparative Evaluation of Machine Learning Models for Anomaly-Based IDS in IoT Networks

Seyed Amir Mousavi - Mostafa Sadeghi - Mohammad Sadeq Sirjani

Sentiment Analysis of the Amazon Customers Using the BiGRU Neural Network Enhanced by Attention Mechanism

Sara Sinan Salman al-Abedi - Keyvan Mohebbi

A Potential Solutions-Based Parallelized GA for Application Graph Mapping in Reconfigurable Hardware

Seyed Mehdi Mohtavipour - Hadi Shahriar Shahhoseini

A Mathematical Optimization Approach for Preference Learning in Movie Recommender Systems with Shared Accounts

Milad Khademali - Fazlollah Aghamohammadi - Marjan Kaedi - Alireza Nasiri

more

Samin Hamayesh - Version 42.5.2