# Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations

arXiv: https://arxiv.org/abs/2610.16627 · HTML: https://mlsanity.com/paper/2610.16627/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 77 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanations](https://mlsanity.com/paper/1912.09024/) (2019)
- [On the Explainability of Natural Language Processing Deep Models](https://mlsanity.com/paper/2210.06929/) (2022)
- [Human-in-the-Loop Interpretability Prior](https://mlsanity.com/paper/1805.11571/) (2018)
- [Evaluating Explanation Without Ground Truth in Interpretable Machine Learning](https://mlsanity.com/paper/1907.06831/) (2019)
- [Interpretable by Design: Learning Predictors by Composing Interpretable Queries](https://mlsanity.com/paper/2207.00938/) (2022)
- [Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability](https://mlsanity.com/paper/2010.13764/) (2020)
- [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](https://mlsanity.com/paper/2211.05667/) (2022)
- [Scale Alone Does not Improve Mechanistic Interpretability in Vision Models](https://mlsanity.com/paper/2307.05471/) (2023)
- [An Objective Metric for Explainable AI: How and Why to Estimate the Degree of Explainability](https://mlsanity.com/paper/2109.05327/) (2021)
- [Cost-Sensitive Feature Selection by Optimizing F-Measures](https://mlsanity.com/paper/1904.02301/) (2019)
- [Toward Understanding the Disagreement Problem in Neural Network Feature Attribution](https://mlsanity.com/paper/2404.11330/) (2024)
- [Reasoning-Grounded Natural Language Explanations for Language Models](https://mlsanity.com/paper/2503.11248/) (2025)
- [For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI](https://mlsanity.com/paper/2306.07637/) (2023)
- [Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures](https://mlsanity.com/paper/2604.16042/) (2026)
- [Towards Feature Engineering at Scale for Data from Massive Open Online Courses](https://mlsanity.com/paper/1407.5238/) (2014)
- [Cost-sensitive Feature Selection for Support Vector Machines](https://mlsanity.com/paper/2401.07627/) (2024)
- [Predicting Satisfaction of Counterfactual Explanations from Human Ratings of Explanatory Qualities](https://mlsanity.com/paper/2504.13899/) (2025)
- [The Feature Understandability Scale for Human-Centred Explainable AI: Assessing Tabular Feature Importance](https://mlsanity.com/paper/2510.07050/) (2025)

## Abstract (arXiv)

Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable insights into improving accessibility. This study incorporates human-based feature understandability into feature selection to improve the generation of human-centred explanations. Natural language explanations for machine learning models trained on tabular data often cite influential features in the input data to explain a given decision. As a consequence, users' ability to understand the produced explanation hinges on their understanding of the cited features. To quantify this natural-language feature understandability, Rossberg et al. proposed the Feature Understandability Scale, which assigns numerical `understandability scores' to features based on user feedback. To evaluate the degree to which these scores can improve machine learning explanation quality, this study collects understandability scores across two datasets, proposes an understandability-aware feature selection algorithm to select features that are both understandable and informative, and trains a random forest based on these feature subsets. The SHAP-based explanations generated by this model are evaluated using user feedback, and changes in explanation quality are assessed. The individual evaluation of the explanations showed that while the understandability-based explanations scored higher on average, the difference was not statistically significant. In contrast, the comparative evaluation found that participants preferred these explanations significantly more frequently than expected at the chance level. It is concluded that the integration of understandability can yield more understandable explanations at minimal cost to classification performance, although changes to quality require elucidation in larger cohorts.