mlsanityData to 7 Oct 2026

Contestable AI needs Computational Argumentation

arXiv 2405.10729 ↗First posted 17 May 2024cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable. Instead, contestability is advocated by AI guidelines (e.g. by the OECD) and regulation of automated decision-making (e.g. GDPR). In this position paper we explore how contestability can be achieved computationally in and for AI. We argue that contestable AI requires dynamic (human-machine and/or machine-machine) explainability and decision-making processes, whereby machines can (i) interact with humans and/or other machines to progressively explain their outputs and/or their reasoning as well as assess grounds for contestation provided by these humans and/or other machines, and (ii) revise their decision-making processes to redress any issues successfully raised during contestation. Given that much of the current AI landscape is tailored to static AIs, the need to accommodate contestability will require a radical rethinking, that, we argue, computational argumentation is ideally suited to support.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 36 of its 128 references that are in the map. First posted on arXiv 17 May 2024.

Builds on

36 of 128 references.

References · 36

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  4. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  5. 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,130
  6. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  7. 2020Artificial Intelligence, Values and Alignmentcited by 443
  8. 2016Cooperative Inverse Reinforcement Learningcited by 298
  9. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  10. 2018Abduction-Based Explanations for Machine Learning Modelscited by 159
  11. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 144
  12. 2019Optimal Policies Tend to Seek Powercited by 115
24 more
  1. 2016The Off-Switch Gamecited by 97
  2. 2021AI in Finance: Challenges, Techniques and Opportunitiescited by 81
  3. 2017Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweakingcited by 76
  4. 2016Research Priorities for Robust and Beneficial Artificial Intelligencecited by 74
  5. 2021Argumentative XAI: A Surveycited by 66
  6. 2023Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision supportcited by 65
  7. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  8. 2020FIND: Human-in-the-Loop Debugging Deep Text Classifierscited by 40
  9. 2022Formalising the Robustness of Counterfactual Explanations for Neural Networkscited by 24
  10. 2023Interactive Explanations by Conflict Resolution via Argumentative Exchangescited by 24
  11. 2019A Grounded Interaction Protocol for Explainable Artificial Intelligencecited by 22
  12. 2023From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Spacecited by 20
  13. 2021Surrogate Model-Based Explainability Methods for Point Cloud NNscited by 18
  14. 2023SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]cited by 18
  15. 2020Machine Guides, Human Supervises: Interactive Learning with Global Explanationscited by 16
  16. 2020Three Modern Roles for Logic in AIcited by 15
  17. 2023Contestable Camera Cars: A Speculative Design Exploration of Public AI That Is Open and Responsive to Disputecited by 9
  18. 2019Culture-Based Explainable Human-Agent Deconflictioncited by 7
  19. 2020Contestable Black Boxescited by 6
  20. 2021Machine Learning for Utility Prediction in Argument-Based Computational Persuasioncited by 6
  21. 2022Causal Discovery and Knowledge Injection for Contestable Neural Networks (with Appendices)cited by 6
  22. 2014Change in Abstract Argumentation Frameworks: Adding an Argumentcited by 4
  23. 2021Agree to Disagree: Subjective Fairness in Privacy-Restricted Decentralised Conflict Resolutioncited by 3
  24. 2023Targeted Activation Penalties Help CNNs Ignore Spurious Signalscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 5.

12 papers.

  1. 2026Argumentation for Explainable and Globally Contestable Decision Support with LLMscited by 3
  2. 2025Explainable AI Systems Must Be Contestable: Here's How to Make It Happencited by 2
  3. 2025Set Contribution Functions for Quantitative Bipolar Argumentation and their Principlescited by 2
  4. 2025Argumentative Ensembling for Robust Recourse under Model Multiplicitycited by 1
  5. 2025Think, Act, Learn: A Framework for Autonomous Robotic Agents using Closed-Loop Large Language Modelscited by 1
  6. 2025Aristotle's Original Idea: For and Against Logic in the era of AIcited by 0
  7. 2025Am I Being Treated Fairly? A Conceptual Framework for Individuals to Ascertain Fairnesscited by 0
  8. 2025Multi-User Personalisation in Human-Robot Interaction: Resolving Preference Conflicts Using Gradual Argumentationcited by 0
  9. 2026ART: Adaptive Reasoning Trees for Explainable Claim Verificationcited by 0
  10. 2026CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphscited by 0
  11. 2026Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Plan Coordinationcited by 0
  12. 2026Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiencescited by 0