# EXAGREE: Mitigating Explanation Disagreement with Stakeholder-Aligned Models

arXiv: https://arxiv.org/abs/2411.01956 · HTML: https://mlsanity.com/paper/2411.01956/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 4 Nov 2024.

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

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Explainable Machine Learning for Scientific Insights and Discoveries](https://mlsanity.com/paper/1905.08883/) (2019)
- [Fairness in Machine Learning: Lessons from Political Philosophy](https://mlsanity.com/paper/1712.03586/) (2017)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [Differentiable Ranks and Sorting using Optimal Transport](https://mlsanity.com/paper/1905.11885/) (2019)
- [Stochastic Optimization of Sorting Networks via Continuous Relaxations](https://mlsanity.com/paper/1903.08850/) (2019)
- [Exploring the Whole Rashomon Set of Sparse Decision Trees](https://mlsanity.com/paper/2209.08040/) (2022)
- [Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs](https://mlsanity.com/paper/2004.11440/) (2020)
- [Amazing Things Come From Having Many Good Models](https://mlsanity.com/paper/2407.04846/) (2024)
- [On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products](https://mlsanity.com/paper/1610.01256/) (2016)
- [Rashomon Capacity: A Metric for Predictive Multiplicity in Classification](https://mlsanity.com/paper/2206.01295/) (2022)
- [Reliable and Explainable Machine Learning Methods for Accelerated Material Discovery](https://mlsanity.com/paper/1901.02717/) (2019)
- [BEExAI: Benchmark to Evaluate Explainable AI](https://mlsanity.com/paper/2407.19897/) (2024)
- [Exploring the cloud of feature interaction scores in a Rashomon set](https://mlsanity.com/paper/2305.10181/) (2023)
- [Variance Tolerance Factors For Interpreting ALL Neural Networks](https://mlsanity.com/paper/2209.13858/) (2022)
- [Explain To Decide: A Human-Centric Review on the Role of Explainable Artificial Intelligence in AI-assisted Decision Making](https://mlsanity.com/paper/2312.11507/) (2023)

## Abstract (arXiv)

Conflicting explanations, arising from different attribution methods or model internals, limit the adoption of machine learning models in safety-critical domains. We turn this disagreement into an advantage and introduce EXplanation AGREEment (EXAGREE), a two-stage framework that selects a Stakeholder-Aligned Explanation Model (SAEM) from a set of similar-performing models. The selection maximizes Stakeholder-Machine Agreement (SMA), a single metric that unifies faithfulness and plausibility. EXAGREE couples a differentiable mask-based attribution network (DMAN) with monotone differentiable sorting, enabling gradient-based search inside the constrained model space. Experiments on six real-world datasets demonstrate simultaneous gains of faithfulness, plausibility, and fairness over baselines, while preserving task accuracy. Extensive ablation studies, significance tests, and case studies confirm the robustness and feasibility of the method in practice.