Expanding Explainability: Towards Social Transparency in AI systems
arXiv:2101.04719 · doi:10.1145/3411764.3445188
Abstract
As AI-powered systems increasingly mediate consequential decision-making, their explainability is critical for end-users to take informed and accountable actions. Explanations in human-human interactions are socially-situated. AI systems are often socio-organizationally embedded. However, Explainable AI (XAI) approaches have been predominantly algorithm-centered. We take a developmental step towards socially-situated XAI by introducing and exploring Social Transparency (ST), a sociotechnically informed perspective that incorporates the socio-organizational context into explaining AI-mediated decision-making. To explore ST conceptually, we conducted interviews with 29 AI users and practitioners grounded in a speculative design scenario. We suggested constitutive design elements of ST and developed a conceptual framework to unpack ST's effect and implications at the technical, decision-making, and organizational level. The framework showcases how ST can potentially calibrate trust in AI, improve decision-making, facilitate organizational collective actions, and cultivate holistic explainability. Our work contributes to the discourse of Human-Centered XAI by expanding the design space of XAI.
Accepted to CHI2021
References in corpus (14)
- Towards A Rigorous Science of Interpretable Machine Learning
- Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence
- Explaining Explanations in AI
- Questioning the AI: Informing Design Practices for Explainable AI User Experiences
- Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
- One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
- explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
- Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems
- Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgment
- Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes
- Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs
- Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions
- Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study
- TED: Teaching AI to Explain its Decisions
Cited by in corpus (55)
- Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
- Design Principles for Generative AI Applications
- "Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
- Designing for Responsible Trust in AI Systems: A Communication Perspective
- Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systems
- Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI
- XAIR: A Framework of Explainable AI in Augmented Reality
- Better Together? An Evaluation of AI-Supported Code Translation
- Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory
- Towards Relatable Explainable AI with the Perceptual Process
- Writer-Defined AI Personas for On-Demand Feedback Generation
- Human-Centered Responsible Artificial Intelligence: Current & Future Trends
- AIdeation: Designing a Human-AI Collaborative Ideation System for Concept Designers
- How Platform-User Power Relations Shape Algorithmic Accountability: A Case Study of Instant Loan Platforms and Financially Stressed Users in India
- Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making
- Seamful XAI: Operationalizing Seamful Design in Explainable AI
- The Algorithmic Imprint
- As Confidence Aligns: Exploring the Effect of AI Confidence on Human Self-confidence in Human-AI Decision Making
- Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support
- Out of Context: Investigating the Bias and Fairness Concerns of "Artificial Intelligence as a Service"
- Path To Gain Functional Transparency In Artificial Intelligence With Meaningful Explainability
- ShapG: new feature importance method based on the Shapley value
- Are We Asking the Right Questions?: Designing for Community Stakeholders' Interactions with AI in Policing
- Explanation Strategies as an Empirical-Analytical Lens for Socio-Technical Contextualization of Machine Learning Interpretability
- How Can We Develop Explainable Systems? Insights from a Literature Review and an Interview Study
- Mapping the Design Space of Teachable Social Media Feed Experiences
- Using ChatGPT in HCI Research -- A Trioethnography
- Perceptions of Sentient AI and Other Digital Minds: Evidence from the AI, Morality, and Sentience (AIMS) Survey
- Human-Centered Explainable AI (XAI): From Algorithms to User Experiences
- AI Rivalry as a Craft: How Resisting and Embracing Generative AI Reshape Writing Professions
- Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models
- DataPilot: Utilizing Quality and Usage Information for Subset Selection during Visual Data Preparation
- The AI-DEC: A Card-based Design Method for User-centered AI Explanations
- Beyond Recommendations: From Backward to Forward AI Support of Pilots' Decision-Making Process
- Design, Development, and Deployment of Context-Adaptive AI Systems for Enhanced End-User Adoption
- The Centers and Margins of Modeling Humans in Well-being Technologies: A Decentering Approach
- The Impact of Expertise in the Loop for Exploring Machine Rationality
- A Framework for Designing Fair Ubiquitous Computing Systems
- Thoughtful Adoption of NLP for Civic Participation: Understanding Differences Among Policymakers
- Linguistically Differentiating Acts and Recalls of Racial Microaggressions on Social Media
- Inclusive Emotion Technologies: Addressing the Needs of d/Deaf and Hard of Hearing Learners in Video-Based Learning
- Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions
- Situated Case Studies for a Human-Centered Design of Explanation User Interfaces
- Towards Feature Engineering with Human and AI's Knowledge: Understanding Data Science Practitioners' Perceptions in Human&AI-Assisted Feature Engineering Design
- On Explainability in AI-Solutions: A Cross-Domain Survey
- Audit and Assurance of AI Algorithms: A framework to ensure ethical algorithmic practices in Artificial Intelligence
- Seven challenges for harmonizing explainability requirements
- From Model Performance to Claim: How a Change of Focus in Machine Learning Replicability Can Help Bridge the Responsibility Gap
- Beyond the Single-Best Model: Rashomon Partial Dependence Profile for Trustworthy Explanations in AutoML
- LEx: A Framework for Operationalising Layers of Machine Learning Explanations
- Towards Better User Requirements: How to Involve Human Participants in XAI Research
- Integrating measures of replicability into scholarly search: Challenges and opportunities
- Accessible and Pedagogically-Grounded Explainability for Human-Robot Interaction: A Framework Based on UDL and Symbolic Interfaces
- A User-Centred Framework for Explainable Artificial Intelligence in Human-Robot Interaction
- Perils of Label Indeterminacy: A Case Study on Prediction of Neurological Recovery After Cardiac Arrest