On Selective, Mutable and Dialogic XAI: a Review of What Users Say about Different Types of Interactive Explanations

Explainability (XAI) has matured in recent years to provide more human-centered explanations of AI-based decision systems. While static explanations remain predominant, interactive XAI has gathered momentum to support the human cognitive process of explaining. However, the evidence regarding the benefits of interactive explanations is unclear. In this paper, we map existing findings by conducting a detailed scoping review of 48 empirical studies in which interactive explanations are evaluated with human users. We also create a classification of interactive techniques specific to XAI and group the resulting categories according to their role in the cognitive process of explanation: "selective", "mutable" or "dialogic". We identify the effects of interactivity on several user-based metrics. We find that interactive explanations improve perceived usefulness and performance of the human+AI team but take longer. We highlight conflicting results regarding cognitive load and overconfidence. Lastly, we describe underexplored areas including measuring curiosity or learning or perturbing outcomes.

• Publication year

  2023

• Venue

  International Conference on Human Factors in Computing Systems

• Publication date

  2023-04-19

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3544548.3581314
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations

  2022cited by this paper
• Investigating Explainability of Generative AI for Code through Scenario-based Design

  2022cited by this paper
• Making Data Tangible: A Cross-disciplinary Design Space for Data Physicalization

  2022cited by this paper
• How Do People Rank Multiple Mutant Agents?

  2022influential reference
• Contextualization and Exploration of Local Feature Importance Explanations to Improve Understanding and Satisfaction of Non-Expert Users

  2022influential reference
• Building Trust in Interactive Machine Learning via User Contributed Interpretable Rules

  2022influential reference
• Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens

  2021cited by this paper
• Evaluating the Interpretability of Generative Models by Interactive Reconstruction

  2021influential reference
• What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research

  2021cited by this paper
• Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs

  2021cited by this paper
• Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies

  2021influential reference
• Nudging through Friction: An Approach for Calibrating Trust in Explainable AI

  2021cited by this paper
• QuestionComb: A Gamification Approach for the Visual Explanation of Linguistic Phenomena through Interactive Labeling

  2021cited by this paper
• Learn, Generate, Rank, Explain: A Case Study of Visual Explanation by Generative Machine Learning

  2021influential reference
• Developing Conversational Agents for Use in Criminal Investigations

  2021influential reference
• Why or Why Not? The Effect of Justification Styles on Chatbot Recommendations

  2021influential reference
• VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models

  2021cited by this paper
• ChatrEx: Designing Explainable Chatbot Interfaces for Enhancing Usefulness, Transparency, and Trust

  2021influential reference
• Towards Visual Explainable Active Learning for Zero-Shot Classification

  2021influential reference
• Conversational review-based explanations for recommender systems: Exploring users’ query behavior

  2021influential reference
• Levels of explainable artificial intelligence for human-aligned conversational explanations

  2021cited by this paper
• Using Explainability to Help Children UnderstandGender Bias in AI

  2021influential reference
• Understanding User Sensemaking in Machine Learning Fairness Assessment Systems

  2021cited by this paper
• Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models

  2021cited by this paper
• Explainable Active Learning (XAL)

  2021cited by this paper
• Exploring and Promoting Diagnostic Transparency and Explainability in Online Symptom Checkers

  2021influential reference
• Data-Centric Explanations: Explaining Training Data of Machine Learning Systems to Promote Transparency

  2021influential reference
• Anchoring Bias Affects Mental Model Formation and User Reliance in Explainable AI Systems

  2021cited by this paper
• I Think I Get Your Point, AI! The Illusion of Explanatory Depth in Explainable AI

  2021cited by this paper
• Visual, textual or hybrid: the effect of user expertise on different explanations

  2021influential reference
• From Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein’s Theory of Explanation

  2021influential reference
• Model learning with personalized interpretability estimation (ML-PIE)

  2021cited by this paper
• XAlgo: a Design Probe of Explaining Algorithms’ Internal States via Question-Answering

  2021influential reference
• To Trust or to Think

  2021cited by this paper
• ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models

  2021cited by this paper
• Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making

  2021influential reference
• Proxy tasks and subjective measures can be misleading in evaluating explainable AI systems

  2020cited by this paper
• One Explanation Does Not Fit All

  2020cited by this paper
• Characterization of Models for Identifying Physical and Cognitive Frailty in Older Adults With Diabetes: Systematic Review and Meta-Analysis

  2020influential reference
• DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models

  2020cited by this paper
• SIMFIC: An Explainable Book Search Companion

  2020cited by this paper
• Explanations:

  2020cited by this paper
• Silva: Interactively Assessing Machine Learning Fairness Using Causality

  2020influential reference
• Bot-Detective: An explainable Twitter bot detection service with crowdsourcing functionalities

  2020cited by this paper
• ExplainExplore: Visual Exploration of Machine Learning Explanations

  2020cited by this paper
• Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

  2020cited by this paper
• Concept Bottleneck Models

  2020cited by this paper
• What Are People Doing About XAI User Experience? A Survey on AI Explainability Research and Practice

  2020cited by this paper
• Mediating Community-AI Interaction through Situated Explanation

  2020cited by this paper
• Questioning the AI: Informing Design Practices for Explainable AI User Experiences

  2020cited by this paper
• Gamut: A Design Probe to Understand How Data Scientists Understand Machine Learning Models

  2019influential reference
• Designing Theory-Driven User-Centric Explainable AI

  2019cited by this paper
• Personalized Explanation for Machine Learning: a Conceptualization

  2019influential reference
• Explainability fact sheets: a framework for systematic assessment of explainable approaches

  2019cited by this paper
• Progressive disclosure: empirically motivated approaches to designing effective transparency

  2019influential reference
• Explaining Decision-Making Algorithms through UI: Strategies to Help Non-Expert Stakeholders

  2019influential reference
• Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

  2019cited by this paper
• To explain or not to explain: the effects of personal characteristics when explaining music recommendations

  2019cited by this paper
• Modeling Individual and Team Behavior through Spatio-temporal Analysis

  2019cited by this paper
• Personalized explanations for hybrid recommender systems

  2019cited by this paper
• AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias

  2019cited by this paper
• One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

  2019cited by this paper
• The effect of explanations and algorithmic accuracy on visual recommender systems of artistic images

  2019cited by this paper
• What makes a good conversation? How controllable attributes affect human judgments

  2019cited by this paper
• explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning

  2019cited by this paper
• DeepClue: Visual Interpretation of Text-Based Deep Stock Prediction

  2019cited by this paper
• Procedural Justice in Algorithmic Fairness

  2019cited by this paper
• RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

  2018cited by this paper
• RuleMatrix: Visualizing and Understanding Classifiers with Rules

  2018influential reference
• PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation

  2018cited by this paper
• Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

  2018cited by this paper
• What can AI do for me?: evaluating machine learning interpretations in cooperative play

  2018cited by this paper
• CarePre

  2018cited by this paper
• Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach

  2018cited by this paper
• Metrics for Explainable AI: Challenges and Prospects

  2018influential reference
• Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda

  2018cited by this paper
• 'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions

  2018cited by this paper
• A practical approach to measuring user engagement with the refined user engagement scale (UES) and new UES short form

  2018cited by this paper
• Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges

  2018cited by this paper
• Visualizing Ubiquitously Sensed Measures of Motor Ability in Multiple Sclerosis

  2018cited by this paper
• Toward Foraging for Understanding of StarCraft Agents: An Empirical Study

  2017cited by this paper
• The Meaning of Interactivity—Some Proposals for Definitions and Measures

  2017cited by this paper
• How People Explain Action (and Autonomous Intelligent Systems Should Too)

  2017influential reference
• Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

  2017cited by this paper
• Explanation in Artificial Intelligence: Insights from the Social Sciences

  2017influential reference
• Towards A Rigorous Science of Interpretable Machine Learning

  2017influential reference
• Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models

  2016cited by this paper
• “Why Should I Trust You?”: Explaining the Predictions of Any Classifier

  2016cited by this paper
• Interactivity in online discussions and learning outcomes

  2016cited by this paper
• What Synthesis Methodology Should I Use? A Review and Analysis of Approaches to Research Synthesis

  2016cited by this paper
• Measuring Justice and Fairness

  2015cited by this paper
• Principles of Explanatory Debugging to Personalize Interactive Machine Learning

  2015cited by this paper
• Getting the Message?: A Study of Explanation Interfaces for Microblog Data Analysis

  2015cited by this paper
• The Oxford handbook of justice in the workplace

  2015cited by this paper
• Explaining the user experience of recommender systems

  2012cited by this paper
• Trust in a specific technology: An investigation of its components and measures

  2011cited by this paper
• Designing interactivity in media interfaces: a communications perspective

  2010cited by this paper
• 引言 (Introduction)

  2009cited by this paper
• Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement

  2009cited by this paper
• Preferred reporting items for systematic reviews and meta-analyses: the PRISMA Statement

  2009cited by this paper

• Emergent, not Immanent: A Baradian Reading of Explainable AI

  2026cites this paper
• Generation and evaluation of adaptive explanations based on dynamic partner-modeling and non-stationary decision making

  2026cites this paper
• Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework

  2025cites this paper
• Direct Preference Optimization for Adaptive Concept-based Explanations

  2025cites this paper
• Navigating the informativeness-compression trade-off in XAI

  2025cites this paper
• Explainability, Robustness, and Fairness in User-Centric Intelligent Systems: A Systematic Review

  2025cites this paper
• Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI

  2025cites this paper
• Explanation User Interfaces: A Systematic Literature Review

  2025cites this paper
• A Three-level Framework for LLM-enhanced Explainable AI: From Technical Explanations to Natural Language

  2025cites this paper
• Beyond the Hype: Mapping Uncertainty and Gratification in AI Assistant Use

  2025cites this paper
• Granular Feedback: Leveraging Domain Expertise and Explainable AI to Effectively Steer Models

  2025cites this paper
• ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations

  2025cites this paper
• Dialogue-Based XAI Approaches: Exploring the Continuum from Static Explanations to Free-Form Chat Interfaces

  2025cites this paper
• Explainable AI for breast cancer risk prediction: evaluating the accuracy-explainability trade-off

  2025cites this paper
• IXAII: An Interactive Explainable Artificial Intelligence Interface for Decision Support Systems

  2025cites this paper
• Human-Centered Explainability in Interactive Information Systems: A Survey

  2025influential citation
• Can AI Explanations Make You Change Your Mind?

  2025cites this paper
• Operationalizing selective transparency using progressive disclosure in artificial intelligence clinical diagnosis systems

  2025cites this paper
• Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems

  2025cites this paper
• Bridging Explainability and Interactivity to foster Trust and increase Interpretability in AI-systems: A Comparative Study on Explainability and Feedback Mechanisms in AI-based OCR

  2025cites this paper
• A Review of Explainable Artificial Intelligence from the Perspectives of Challenges and Opportunities

  2025cites this paper
• Development of Mental Models in Human-AI Collaboration: A Conceptual Framework

  2025cites this paper
• Explainability in carbon price forecasting systems: A systematic literature review

  2025cites this paper
• Understanding Human-Machine Team Communication from an Explainable-AI Perspective

  2025cites this paper
• Redefining academic integrity: patterns of assignment cheating with generative AI tools

  2025cites this paper
• Towards Co-Constructed Explanations: A Multi-Agent Reasoning-Based Conversational System for Adaptive Explanations

  2025cites this paper
• Human-centered explanation does not fit all: The interplay of sociotechnical, cognitive, and individual factors in the effect AI explanations in algorithmic decision-making

  2025cites this paper
• Designing Explainable and Counterfactual-Based AI Interfaces for Operators in Process Industries

  2025influential citation
• Explaining AI weaknesses improves human-AI performance in a dynamic control task

  2025cites this paper
• Explainable artificial intelligence for energy systems maintenance: A review on concepts, current techniques, challenges, and prospects

  2025cites this paper
• Discernibility in explanations: an approach to designing more acceptable and meaningful machine learning models for medicine

  2025cites this paper
• "Here the GPT made a choice, and every choice can be biased": How Students Critically Engage with LLMs through End-User Auditing Activity

  2025cites this paper
• Questioning the Robot: Using Human Non-verbal Cues to Estimate the Need for Explanations

  2025cites this paper
• Rhetorical XAI: Explaining AI's Benefits as well as its Use via Rhetorical Design

  2025cites this paper
• SNAPE-PM: Building and Utilizing Dynamic Partner Models for Adaptive Explanation Generation

  2025cites this paper
• Integration of User-Centered Design in the Development of Big Data and Machine Learning-Based Applications: A Systematic Mapping Study

  2024cites this paper
• EXMOS: Explanatory Model Steering through Multifaceted Explanations and Data Configurations

  2024cites this paper
• Towards AI Accountability Infrastructure: Gaps and Opportunities in AI Audit Tooling

  2024cites this paper
• Explainability in JupyterLab and Beyond: Interactive XAI Systems for Integrated and Collaborative Workflows

  2024influential citation
• ``It Is a Moving Process": Understanding the Evolution of Explainability Needs of Clinicians in Pulmonary Medicine

  2024cites this paper
• An Explanatory Model Steering System for Collaboration between Domain Experts and AI

  2024cites this paper
• The AI-DEC: A Card-based Design Method for User-centered AI Explanations

  2024cites this paper
• Meaningful Transparency for Clinicians: Operationalising HCXAI Research with Gynaecologists

  2024cites this paper
• CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems

  2024cites this paper
• XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach

  2024cites this paper
• Envisioning Possibilities and Challenges of AI for Personalized Cancer Care

  2024cites this paper
• The X Factor: On the Relationship between User eXperience and eXplainability

  2024cites this paper
• VIME: Visual Interactive Model Explorer for Identifying Capabilities and Limitations of Machine Learning Models for Sequential Decision-Making

  2024cites this paper
• Where Are We and Where Can We Go on the Road to Reliance-Aware Explainable User Interfaces?

  2024cites this paper
• Outcome First or Overview First? Optimizing Patient-Oriented Framework for Evidence-Based Healthcare Treatment Selections with XAI Tools

  2024cites this paper
• ContractMind: Trust-calibration interaction design for AI contract review tools

  2024cites this paper
• Human-AI collaboration is not very collaborative yet: a taxonomy of interaction patterns in AI-assisted decision making from a systematic review

  2023influential citation
• Designing AI Support for Human Involvement in AI-assisted Decision Making: A Taxonomy of Human-AI Interactions from a Systematic Review

  2023influential citation
• InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations

  2023cites this paper
• The Metacognitive Demands and Opportunities of Generative AI

  2023cites this paper
• Lessons Learned from EXMOS User Studies: A Technical Report Summarizing Key Takeaways from User Studies Conducted to Evaluate The EXMOS Platform

  2023cites this paper
• Computational and Structural Biotechnology Journal

  year unknowncites this paper
• Keep talking and nobody decides How can AI augment users’ ability to detect misinformation while balancing engagement and workload?

  year unknowncites this paper