mlsanityData to 7 Oct 2026

Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI

arXiv 2301.11970 ↗First posted 27 Jan 2023cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

Recently, eXplainable AI (XAI) research has focused on counterfactual explanations as post-hoc justifications for AI-system decisions (e.g. a customer refused a loan might be told: If you asked for a loan with a shorter term, it would have been approved). Counterfactuals explain what changes to the input-features of an AI system change the output-decision. However, there is a sub-type of counterfactual, semi-factuals, that have received less attention in AI (though the Cognitive Sciences have studied them extensively). This paper surveys these literatures to summarise historical and recent breakthroughs in this area. It defines key desiderata for semi-factual XAI and reports benchmark tests of historical algorithms (along with a novel, naieve method) to provide a solid basis for future algorithmic developments.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 29 of its 148 references that are in the map. First posted on arXiv 27 Jan 2023.

Builds on

29 of 148 references.

References · 29

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  6. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  7. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  8. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  9. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  10. 2020Multi-Objective Counterfactual Explanationscited by 157
  11. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  12. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
17 more
  1. 2020Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)cited by 79
  2. 2021Argumentative XAI: A Surveycited by 66
  3. 2020On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learningcited by 60
  4. 2017Relief-Based Feature Selection: Introduction and Reviewcited by 38
  5. 2021GeCo: Quality Counterfactual Explanations in Real Timecited by 32
  6. 2022A Rationale-Centric Framework for Human-in-the-loop Machine Learningcited by 27
  7. 2019Leveraging Latent Features for Local Explanationscited by 21
  8. 2022Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Settingcited by 11
  9. 2022"Even if ..." -- Diverse Semifactual Explanations of Rejectcited by 11
  10. 2021DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoodscited by 10
  11. 2022Identifying Spurious Correlations and Correcting them with an Explanation-based Learningcited by 10
  12. 2021Generating Contrastive Explanations for Inductive Logic Programming Based on a Near Miss Approachcited by 8
  13. 2022This changes to that : Combining causal and non-causal explanations to generate disease progression in capsule endoscopycited by 8
  14. 2022Alterfactual Explanations -- The Relevance of Irrelevance for Explaining AI Systemscited by 7
  15. 2021DeDUCE: Generating Counterfactual Explanations Efficientlycited by 6
  16. 2019Interpreting Neural Networks Using Flip Pointscited by 2
  17. 2021Applying the Case Difference Heuristic to Learn Adaptations from Deep Network Featurescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 10; 2025: 1; 2026: 5.

20 papers.

Sort:

By area:

  1. 2023Natural Example-Based Explainability: a Surveycited by 13
  2. 2024Interpreting Language Reward Models via Contrastive Explanationscited by 9
  3. 2023The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomescited by 8
  4. 2024Even-Ifs From If-Onlys: Are the Best Semi-Factual Explanations Found Using Counterfactuals As Guides?cited by 5
  5. 2024Even-if Explanations: Formal Foundations, Priorities and Complexitycited by 4
  6. 2025From Prototypes to Sparse ECG Explanations: SHAP-Driven Counterfactuals for Multivariate Time-Series Multi-class Classificationcited by 3
  7. 2023Viewing the process of generating counterfactuals as a source of knowledge: a new approach for explaining classifierscited by 2
  8. 2024Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discoverycited by 2
  9. 2024Counterfactual and Semifactual Explanations in Abstract Argumentation: Formal Foundations, Complexity and Computationcited by 2
  10. 2023Iterative Partial Fulfillment of Counterfactual Explanations: Benefits and Riskscited by 1
  11. 2024Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-based Counterfactual Generation Method for Trustworthy Artificial Intelligencecited by 1
  12. 2024Case-based Explainability for Random Forest: Prototypes, Critics, Counter-factuals and Semi-factualscited by 1
8 more
  1. 2024Semifactual Explanations for Reinforcement Learningcited by 1
  2. 2024Exploring the Effect of Explanation Content and Format on User Comprehension and Trust in Healthcarecited by 0
  3. 2024Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainabilitycited by 0
  4. 2026On the Hardness of Computing Counterfactual and Semifactual Explanations in XAIcited by 0
  5. 2026Temporal Sepsis Modeling: a Relational and Explainable-by-Design Frameworkcited by 0
  6. 2026Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefercited by 0
  7. 2026Towards Verified and Targeted Explanations through Formal Methodscited by 0
  8. 2026Explanations-Driven Active Feature Acquisition for Algorithmic Recoursecited by 0