# Knowing What You Cannot Explain: Learning to Reject Low-Quality Explanations

arXiv: https://arxiv.org/abs/2507.12900 · HTML: https://mlsanity.com/paper/2507.12900/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 80 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Builds on (most cited first, 30 of 33)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [Learning to Complement Humans](https://mlsanity.com/paper/2005.00582/) (2020)
- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [Differentiable Learning Under Triage](https://mlsanity.com/paper/2103.08902/) (2021)
- [Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End](https://mlsanity.com/paper/2011.04917/) (2020)
- [Framework for Evaluating Faithfulness of Local Explanations](https://mlsanity.com/paper/2202.00734/) (2022)
- [Leveraging Explanations in Interactive Machine Learning: An Overview](https://mlsanity.com/paper/2207.14526/) (2022)
- [Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong](https://mlsanity.com/paper/2310.12558/) (2023)
- [Classification Under Human Assistance](https://mlsanity.com/paper/2006.11845/) (2020)
- [Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales](https://mlsanity.com/paper/2305.07095/) (2023)
- [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](https://mlsanity.com/paper/2211.05667/) (2022)
- [Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs](https://mlsanity.com/paper/2406.15156/) (2024)
- [Latent Space Explanation by Intervention](https://mlsanity.com/paper/2112.04895/) (2021)
- [AUC-based Selective Classification](https://mlsanity.com/paper/2210.10703/) (2022)
- [Deep Neural Network Benchmarks for Selective Classification](https://mlsanity.com/paper/2401.12708/) (2024)
- [On Formal Feature Attribution and Its Approximation](https://mlsanity.com/paper/2307.03380/) (2023)
- [Unsupervised Anomaly Detection with Rejection](https://mlsanity.com/paper/2305.13189/) (2023)

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

- [Bounded-Abstention Multi-horizon Time-series Forecasting](https://mlsanity.com/paper/2602.04714/) (2026)
- [Concisely Explaining the Doubt: Minimum-Size Abductive Explanations for Linear Models with a Reject Option](https://mlsanity.com/paper/2603.14096/) (2026)

## Abstract (arXiv)

Learning to Reject (LtR) frameworks allow ML models to abstain from uncertain predictions and promote user trust. However, since current LtR strategies focus solely on predictive performance, they completely neglect explanation quality. Low-quality explanations -- whether they inaccurately reflect the model's reasoning or fail to satisfy users -- can severely compromise trust assessments and induce over-reliance on incorrect predictions. We argue that models should abstain from making a prediction when they cannot offer a satisfactory explanation for it and introduce a framework for learning to reject low-quality explanations (LtX) in which predictors are equipped with a rejector that evaluates the explanation quality. Focusing on popular attribution techniques, we propose REX (REjector of low-quality eXplanations), which learns a rejector from explanation quality labels combining machine-side judgments with explicit human annotations to assess explanation quality. Our empirical evaluation demonstrates that method outperforms popular LtR strategies and baselines relying on isolated explanation metrics. Finally, to support future research, we publicly release a novel, larger-scale dataset of 1050 human-annotated machine explanations.