# The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomes

arXiv: https://arxiv.org/abs/2310.18937 · HTML: https://mlsanity.com/paper/2310.18937/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 60 references that are in the map.
- First posted on arXiv 29 Oct 2023.

## Builds on (most cited first, 30 of 32)

- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Actionable Recourse in Linear Classification](https://mlsanity.com/paper/1809.06514/) (2018)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [Model-Agnostic Counterfactual Explanations for Consequential Decisions](https://mlsanity.com/paper/1905.11190/) (2019)
- [Fair Inference On Outcomes](https://mlsanity.com/paper/1705.10378/) (2017)
- [Algorithmic recourse under imperfect causal knowledge: a probabilistic approach](https://mlsanity.com/paper/2006.06831/) (2020)
- [A survey of algorithmic recourse: definitions, formulations, solutions, and prospects](https://mlsanity.com/paper/2010.04050/) (2020)
- [The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations](https://mlsanity.com/paper/1907.09294/) (2019)
- [Exploring the Whole Rashomon Set of Sparse Decision Trees](https://mlsanity.com/paper/2209.08040/) (2022)
- [On the Fairness of Causal Algorithmic Recourse](https://mlsanity.com/paper/2010.06529/) (2020)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)
- [On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning](https://mlsanity.com/paper/2009.06399/) (2020)
- [On the Adversarial Robustness of Causal Algorithmic Recourse](https://mlsanity.com/paper/2112.11313/) (2021)
- [Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice](https://mlsanity.com/paper/2103.14651/) (2021)
- [Interpretable Credit Application Predictions With Counterfactual Explanations](https://mlsanity.com/paper/1811.05245/) (2018)
- [On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations](https://mlsanity.com/paper/2201.09051/) (2022)
- [On the Privacy Risks of Algorithmic Recourse](https://mlsanity.com/paper/2211.05427/) (2022)
- [A Rationale-Centric Framework for Human-in-the-loop Machine Learning](https://mlsanity.com/paper/2203.12918/) (2022)
- [ProPublica's COMPAS Data Revisited](https://mlsanity.com/paper/1906.04711/) (2019)
- [Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI](https://mlsanity.com/paper/2301.11970/) (2023)
- [Consequence-aware Sequential Counterfactual Generation](https://mlsanity.com/paper/2104.05592/) (2021)
- [Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI](https://mlsanity.com/paper/2204.10152/) (2022)
- ["Even if ..." -- Diverse Semifactual Explanations of Reject](https://mlsanity.com/paper/2207.01898/) (2022)
- [Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis](https://mlsanity.com/paper/2201.07135/) (2022)

## Built on by (most cited first, 8 of 8)

- [Even-Ifs From If-Onlys: Are the Best Semi-Factual Explanations Found Using Counterfactuals As Guides?](https://mlsanity.com/paper/2403.00980/) (2024)
- [Even-if Explanations: Formal Foundations, Priorities and Complexity](https://mlsanity.com/paper/2401.10938/) (2024)
- [Semifactual Explanations for Reinforcement Learning](https://mlsanity.com/paper/2409.05435/) (2024)
- [Learning Counterfactual Outcomes Under Rank Preservation](https://mlsanity.com/paper/2502.06398/) (2025)
- [On the Hardness of Computing Counterfactual and Semifactual Explanations in XAI](https://mlsanity.com/paper/2601.09455/) (2026)
- [Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer](https://mlsanity.com/paper/2603.17534/) (2026)
- [Towards Verified and Targeted Explanations through Formal Methods](https://mlsanity.com/paper/2604.14209/) (2026)
- [Explanations-Driven Active Feature Acquisition for Algorithmic Recourse](https://mlsanity.com/paper/2609.12179/) (2026)

## Abstract (arXiv)

When users receive either a positive or negative outcome from an automated system, Explainable AI (XAI) has almost exclusively focused on how to mutate negative outcomes into positive ones by crossing a decision boundary using counterfactuals (e.g., textit"If you earn 2k more, we will accept your loan application"). Here, we instead focus on textitpositive outcomes, and take the novel step of using XAI to optimise them (e.g., textit"Even if you wish to half your down-payment, we will still accept your loan application"). Explanations such as these that employ "even if..." reasoning, and do not cross a decision boundary, are known as semifactuals. To instantiate semifactuals in this context, we introduce the concept of textitGain (i.e., how much a user stands to benefit from the explanation), and consider the first causal formalisation of semifactuals. Tests on benchmark datasets show our algorithms are better at maximising gain compared to prior work, and that causality is important in the process. Most importantly however, a user study supports our main hypothesis by showing people find semifactual explanations more useful than counterfactuals when they receive the positive outcome of a loan acceptance.