# NoMatterXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models

arXiv: https://arxiv.org/abs/2408.10528 · HTML: https://mlsanity.com/paper/2408.10528/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [Multi-Dimensional Gender Bias Classification](https://mlsanity.com/paper/2005.00614/) (2020)
- [On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning](https://mlsanity.com/paper/2009.06399/) (2020)
- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification](https://mlsanity.com/paper/2010.12512/) (2020)
- [Generating Counterfactual Explanations with Natural Language](https://mlsanity.com/paper/1806.09809/) (2018)
- [Alterfactual Explanations -- The Relevance of Irrelevance for Explaining AI Systems](https://mlsanity.com/paper/2207.09374/) (2022)

## Built on by (most cited first, 2 of 2)

- [Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation](https://mlsanity.com/paper/2511.12100/) (2025)
- [Explanations-Driven Active Feature Acquisition for Algorithmic Recourse](https://mlsanity.com/paper/2609.12179/) (2026)

## Abstract (arXiv)

In Explainable AI (XAI), counterfactual explanations (CEs) are a well-studied method to communicate feature relevance through contrastive reasoning of "what if" to explain AI models' predictions. However, they only focus on important (i.e., relevant) features and largely disregard less important (i.e., irrelevant) ones. Such irrelevant features can be crucial in many applications, especially when users need to ensure that an AI model's decisions are not affected or biased against specific attributes such as gender, race, religion, or political affiliation. To address this gap, the concept of alterfactual explanations (AEs) has been proposed. AEs explore an alternative reality of "no matter what", where irrelevant features are substituted with alternative features (e.g., "republicans" -> "democrats") within the same attribute (e.g., "politics") while maintaining a similar prediction output. This serves to validate whether AI model predictions are influenced by the specified attributes. Despite the promise of AEs, there is a lack of computational approaches to systematically generate them, particularly in the text domain, where creating AEs for AI text classifiers presents unique challenges. This paper addresses this challenge by formulating AE generation as an optimization problem and introducing MoMatterXAI, a novel algorithm that generates AEs for text classification tasks. Our approach achieves high fidelity of up to 95% while preserving context similarity of over 90% across multiple models and datasets. A human study further validates the effectiveness of AEs in explaining AI text classifiers to end users. All codes will be publicly available.