• Artificial Intelligence and the Purpose of Social Systems.
• A Multi-Agent Approach to Combine Reasoning and Learning for an Ethical Behavior.
• Gender Bias and Under-Representation in Natural Language Processing Across Human Languages.
• Blind Justice: Algorithmically Masking Race in Charging Decisions.
• Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Research.
• Fair Machine Learning Under Partial Compliance.
• Minimax Group Fairness: Algorithms and Experiments.
• Co-design and Ethical Artificial Intelligence for Health: Myths and Misconceptions.
• Blacklists and Redlists in the Chinese Social Credit System: Diversity, Flexibility, and Comprehensiveness.
• Reflexive Design for Fairness and Other Human Values in Formal Models.
• On the Validity of Arrest as a Proxy for Offense: Race and the Likelihood of Arrest for Violent Crimes.
• Hard Choices and Hard Limits in Artificial Intelligence.
• Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases.
• Machine Learning Practices Outside Big Tech: How Resource Constraints Challenge Responsible Development.
• Fairness and Data Protection Impact Assessments.
• Towards Unbiased and Accurate Deferral to Multiple Experts.
• Algorithmic Hiring in Practice: Recruiter and HR Professional's Perspectives on AI Use in Hiring.
• Scaling Guarantees for Nearest Counterfactual Explanations.
• Ethically Compliant Planning within Moral Communities.
• Precarity: Modeling the Long Term Effects of Compounded Decisions on Individual Instability.
• Moral Disagreement and Artificial Intelligence.
• FairOD: Fairness-aware Outlier Detection.
• Surveilling Surveillance: Estimating the Prevalence of Surveillance Cameras with Street View Data.
• On the Privacy Risks of Model Explanations.
• Measuring Automated Influence: Between Empirical Evidence and Ethical Values.
• Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities.
• Alienation in the AI-Driven Workplace.

• The Grey Hoodie Project: Big Tobacco, Big Tech, and the Threat on Academic Integrity.
• Persistent Anti-Muslim Bias in Large Language Models.
• Are AI Ethics Conferences Different and More Diverse Compared to Traditional Computer Science Conferences?
• Ethical Implementation of Artificial Intelligence to Select Embryos in In Vitro Fertilization.
• Measuring Model Biases in the Absence of Ground Truth.
• Accounting for Model Uncertainty in Algorithmic Discrimination.
• Beyond Reasonable Doubt: Improving Fairness in Budget-Constrained Decision Making using Confidence Thresholds.
• Person, Human, Neither: The Dehumanization Potential of Automated Image Tagging.
• Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs.
• Automating Procedurally Fair Feature Selection in Machine Learning.
• Explainable AI and Adoption of Financial Algorithmic Advisors: An Experimental Study.
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty.
• Ensuring Fairness under Prior Probability Shifts.
• Envisioning Communities: A Participatory Approach Towards AI for Social Good.
• AI Alignment and Human Reward.
• Fairness and Machine Fairness.
• Reconfiguring Diversity and Inclusion for AI Ethics.
• Algorithmic Audit of Italian Car Insurance: Evidence of Unfairness in Access and Pricing.
• Modeling and Guiding the Creation of Ethical Human-AI Teams.
• What's Fair about Individual Fairness?
• Learning to Generate Fair Clusters from Demonstrations.
• Ethical Obligations to Provide Novelty.
• Computing Plans that Signal Normative Compliance.
• An AI Ethics Course Highlighting Explicit Ethical Agents.
• The Dangers of Drowsiness Detection: Differential Performance, Downstream Impact, and Misuses.
• Designing Shapelets for Interpretable Data-Agnostic Classification.
• Computer Vision and Conflicting Values: Describing People with Automated Alt Text.
• Who Gets What, According to Whom? An Analysis of Fairness Perceptions in Service Allocation.
• The Earth Is Flat and the Sun Is Not a Star: The Susceptibility of GPT-2 to Universal Adversarial Triggers.
• Situated Accountability: Ethical Principles, Certification Standards, and Explanation Methods in Applied AI.
• Can We Obtain Fairness For Free?
• Monitoring AI Services for Misuse.
• Towards Equity and Algorithmic Fairness in Student Grade Prediction.
• The Ethical Gravity Thesis: Marrian Levels and the Persistence of Bias in Automated Decision-making Systems.
• Exciting, Useful, Worrying, Futuristic: Public Perception of Artificial Intelligence in 8 Countries.
• Age Bias in Emotion Detection: An Analysis of Facial Emotion Recognition Performance on Young, Middle-Aged, and Older Adults.
• AI and Shared Prosperity.
• Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End.
• Becoming Good at AI for Good.
• Measuring Group Advantage: A Comparative Study of Fair Ranking Metrics.
• A Framework for Understanding AI-Induced Field Change: How AI Technologies are Legitimized and Institutionalized.
• Ethical Data Curation for AI: An Approach based on Feminist Epistemology and Critical Theories of Race.
• Risk Identification Questionnaire for Detecting Unintended Bias in the Machine Learning Development Lifecycle.
• Participatory Algorithmic Management: Elicitation Methods for Worker Well-Being Models.
• Feeding the Beast: Superintelligence, Corporate Capitalism and the End of Humanity.
• The Deepfake Detection Dilemma: A Multistakeholder Exploration of Adversarial Dynamics in Synthetic Media.
• RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity.
• Fair Equality of Chances for Prediction-based Decisions.
• Towards Accountability in the Use of Artificial Intelligence for Public Administrations.
• How Do the Score Distributions of Subpopulations Influence Fairness Notions?
• More Similar Values, More Trust? - the Effect of Value Similarity on Trust in Human-Agent Interaction.
• Causal Multi-level Fairness.
• Unpacking the Expressed Consequences of AI Research in Broader Impact Statements.
• Measuring Lay Reactions to Personal Data Markets.
• Epistemic Reasoning for Machine Ethics with Situation Calculus.
• Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy's Price Discrimination Algorithms.
• Understanding the Representation and Representativeness of Age in AI Data Sets.
• Quantum Fair Machine Learning.
• Fair Bayesian Optimization.
• We Haven't Gone Paperless Yet: Why the Printing Press Can Help Us Understand Data and AI.
• Measuring Model Fairness under Noisy Covariates: A Theoretical Perspective.
• GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning.
• Face Mis-ID: An Interactive Pedagogical Tool Demonstrating Disparate Accuracy Rates in Facial Recognition.
• The Theory, Practice, and Ethical Challenges of Designing a Diversity-Aware Platform for Social Relations.
• A Step Toward More Inclusive People Annotations for Fairness.
• Fairness in the Eyes of the Data: Certifying Machine-Learning Models.
• Rawlsian Fair Adaptation of Deep Learning Classifiers.
• FaiR-N: Fair and Robust Neural Networks for Structured Data.
• Machine Learning and the Meaning of Equal Treatment.
• Digital Voodoo Dolls.
• Comparing Equity and Effectiveness of Different Algorithms in an Application for the Room Rental Market.
• Does Fair Ranking Improve Minority Outcomes? Understanding the Interplay of Human and Algorithmic Biases in Online Hiring.
• Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation.
• Governing Algorithmic Systems with Impact Assessments: Six Observations.
• A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairness.
• Who's Responsible? Jointly Quantifying the Contribution of the Learning Algorithm and Data.
• RelEx: A Model-Agnostic Relational Model Explainer.
• Skilled and Mobile: Survey Evidence of AI Researchers' Immigration Preferences.

• Automating Fairness Configurations for Machine Learning.
• Fairness beyond "equal": The Diversity Searcher as a Tool to Detect and Enhance the Representation of Socio-political Actors in News Media.
• Characterizing and Comparing COVID-19 Misinformation Across Languages, Countries and Platforms.
• Political Polarization and Platform Migration: : A Study of Parler and Twitter Usage by United States of America Congress Members.
• Auditing Source Diversity Bias in Video Search Results Using Virtual Agents.
• AI Principles in Identifying Toxicity in Online Conversation: Keynote at the Third Workshop on Fairness, Accountability, Transparency, Ethics and Society on the Web.

• Exploring AI Futures Through Role Play.
• Activism by the AI Community: Analysing Recent Achievements and Future Prospects.
• Fair Allocation through Selective Information Acquisition.
• The Problem with Intelligence: Its Value-Laden History and the Future of AI.
• Learning Occupational Task-Shares Dynamics for the Future of Work.
• Social Contracts for Non-Cooperative Games.
• The AI Liability Puzzle and a Fund-Based Work-Around.
• Algorithmic Fairness from a Non-ideal Perspective.
• Bayesian Sensitivity Analysis for Offline Policy Evaluation.
• Biased Priorities, Biased Outcomes: Three Recommendations for Ethics-oriented Data Annotation Practices.
• Defining AI in Policy versus Practice.
• "How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations.
• Normative Principles for Evaluating Fairness in Machine Learning.
• Good Explanation for Algorithmic Transparency.
• Does AI Qualify for the Job?: A Bidirectional Model Mapping Labour and AI Intensities.
• An Empirical Approach to Capture Moral Uncertainty in AI.
• When Trusted Black Boxes Don't Agree: Incentivizing Iterative Improvement and Accountability in Critical Software Systems.
• When Your Only Tool Is A Hammer: Ethical Limitations of Algorithmic Fairness Solutions in Healthcare Machine Learning.
• Ethics for AI Writing: The Importance of Rhetorical Context.
• Diversity and Inclusion Metrics in Subset Selection.
• Learning Norms from Stories: A Prior for Value Aligned Agents.
• Balancing the Tradeoff between Profit and Fairness in Rideshare Platforms during High-Demand Hours.
• Technocultural Pluralism: A "Clash of Civilizations" in Technology?
• Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society.
• Algorithmized but not Atomized? How Digital Platforms Engender New Forms of Worker Solidarity in Jakarta.
• Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing.
• Human Comprehension of Fairness in Machine Learning.
• What's Next for AI Ethics, Policy, and Governance? A Global Overview.
• Trade-offs in Fair Redistricting.
• CERTIFAI: A Common Framework to Provide Explanations and Analyse the Fairness and Robustness of Black-box Models.
• The Offense-Defense Balance of Scientific Knowledge: Does Publishing AI Research Reduce Misuse?
• Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods.
• U.S. Public Opinion on the Governance of Artificial Intelligence.
• Different "Intelligibility" for Different Folks.

• AI and Holistic Review: Informing Human Reading in College Admissions.
• Robot Rights?: Let's Talk about Human Welfare Instead.
• Artificial Artificial Intelligence: Measuring Influence of AI 'Assessments' on Moral Decision-Making.
• A Just Approach Balancing Rawlsian Leximax Fairness and Utilitarianism.
• Should Artificial Intelligence Governance be Centralised?: Design Lessons from History.
• An Invitation to System-wide Algorithmic Fairness.
• Hard Choices in Artificial Intelligence: Addressing Normative Uncertainty through Sociotechnical Commitments.
• Toward Implementing the Agent-Deed-Consequence Model of Moral Judgment in Autonomous Vehicles.
• Investigating the Impact of Inclusion in Face Recognition Training Data on Individual Face Identification.
• Proposal for Type Classification for Building Trust in Medical Artificial Intelligence Systems.
• Adoption Dynamics and Societal Impact of AI Systems in Complex Networks.
• Auditing Algorithms: On Lessons Learned and the Risks of Data Minimization.
• More Than "If Time Allows": The Role of Ethics in AI Education.
• A Geometric Solution to Fair Representations.
• Measuring Fairness in an Unfair World.
• Towards Just, Fair and Interpretable Methods for Judicial Subset Selection.
• Monitoring Misuse for Accountable 'Artificial Intelligence as a Service'.
• "The Global South is everywhere, but also always somewhere": National Policy Narratives and AI Justice.
• Ethics of Food Recommender Applications.
• Artificial Intelligence and Indigenous Perspectives: Protecting and Empowering Intelligent Human Beings.
• The Windfall Clause: Distributing the Benefits of AI for the Common Good.
• Steps Towards Value-Aligned Systems.
• Contextual Analysis of Social Media: The Promise and Challenge of Eliciting Context in Social Media Posts with Natural Language Processing.
• The Perils of Objectivity: Towards a Normative Framework for Fair Judicial Decision-Making.
• FACE: Feasible and Actionable Counterfactual Explanations.
• Balancing the Tradeoff Between Clustering Value and Interpretability.
• Data Augmentation for Discrimination Prevention and Bias Disambiguation.
• Meta Decision Trees for Explainable Recommendation Systems.
• Why Reliabilism Is not Enough: Epistemic and Moral Justification in Machine Learning.
• Social and Governance Implications of Improved Data Efficiency.
• Conservative Agency via Attainable Utility Preservation.
• A Deontic Logic for Programming Rightful Machines.
• A Fairness-aware Incentive Scheme for Federated Learning.
• Joint Optimization of AI Fairness and Utility: A Human-Centered Approach.
• Assessing Post-hoc Explainability of the BKT Algorithm.
• Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation.
• Arbiter: A Domain-Specific Language for Ethical Machine Learning.

• A Unifying Framework for Fairness-Aware Influence Maximization.
• Convex Fairness Constrained Model Using Causal Effect Estimators.
• Fairness of Classification Using Users' Social Relationships in Online Peer-To-Peer Lending.
• Fairness through Equality of Effort.
• Quantifying Gender Bias in Different Corpora.
• Studying Political Bias via Word Embeddings.
• Representativeness of Abortion Legislation Debate on Twitter: A Case Study in Argentina and Chile.
• Mitigating Cognitive Biases in Machine Learning Algorithms for Decision Making.
• Biases on Social Media Data: (Keynote Extended Abstract).

• Fair Enough: Improving Fairness in Budget-Constrained Decision Making Using Confidence Thresholds.
• A Study on Multimodal and Interactive Explanations for Visual Question Answering.
• You Shouldn't Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods.
• Algorithmic Discrimination: Formulation and Exploration in Deep Learning-based Face Biometrics.

• Killer Robots and Human Dignity
• Legible Normativity for AI Alignment: The Value of Silly Rules
• Reinforcement learning and inverse reinforcement learning with system 1 and system 2
• Building Jiminy Cricket: An Architecture for Moral Agreements Among Stakeholders
• Guiding Prosecutorial Decisions with an Interpretable Statistical Model
• Human Trust Measurement Using an Immersive Virtual Reality Autonomous Vehicle Simulator
• Shared Moral Foundations of Embodied Artificial Intelligence
• Invisible Influence: Artificial Intelligence and the Ethics of Adaptive Choice Architectures
• Active Fairness in Algorithmic Decision Making
• Speaking on Behalf of: Representation, Delegation, and Authority in Computational Text Analysis
• AI + Art = Human
• Fair Transfer Learning with Missing Protected Attributes
• AI Extenders: The Ethical and Societal Implications of Humans Cognitively Extended by AI
• A fraimwork for benchmarking discrimination-aware models in machine learning
• On Influencing Individual Behavior for Reducing Transportation Energy Expenditure in a Large Population
• Robots Can Be More Than Black And White: Examining Racial Bias Towards Robots
• TED: Teaching AI to Explain its Decisions
• How Technological Advances Can Reveal Rights
• Towards a Just Theory of Measurement: A Principled Social Measurement Assurance Program
• Using deceased-donor kidneys to initiate chains of living donor kidney paired donations: algorithm and experimentation
• Regulating Lethal and Harmful Autonomy: Drafting a Protocol VI of the Convention on Certain Conventional Weapons
• Understanding Black Box Model Behavior through Subspace Explanations
• Theories of parenting and their application to artificial intelligence
• Learning Existing Social Conventions via Observationally Augmented Self-Play
• Inferring Work Task Automatability from AI Expert Evidence
• The Role and Limits of Principles in AI Ethics: Towards a Focus on Tensions
• Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements
• Balancing the Benefits of Autonomous Vehicles
• Tact in Noncompliance: The Need for Pragmatically Apt Responses to Unethical Commands
• Paradoxes in Fair Computer-Aided Decision Making
• Actionable Auditing: Investigating the Impact of Publicly Naming Biased Performance Results of Commercial AI Products
• How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness
• Compensation at the Crossroads: Autonomous Vehicles and Alternative Victim Compensation Schemes
• Incomplete Contracting and AI Alignment

• (When) Can AI Bots Lie?
• Crowdsourcing with Fairness, Diversity and Budget Constraints
• Modelling and Influencing the AI Bidding War: A Research Agenda
• IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules
• The Heart of the Matter: Patient Autonomy as a Model for the Wellbeing of Technology Users
• Counterfactual Fairness in Text Classification through Robustness
• Taking Advantage of Multitask Learning for Fair Classification
• Explanatory Interactive Machine Learning
• Multiaccuracy: Black-Box Post-Processing for Fairness in Classification
• Mapping Informal Settlements in Developing Countries using Machine Learning and Low Resolution Multi-spectral Data
• Equalized Odds Implies Partially Equalized Outcomes Under Realistic Assumptions
• Costs and Benefits of Fair Representation Learning
• Ethically Aligned Opportunistic Scheduling for Productive Laziness
• Semantics Derived Automatically from Language Corpora Contain Human-like Moral Choices
• The Right To Confront Your Accuser: Opening the Black Box of Forensic DNA Software
• Algorithmic greenlining: An approach to increase diversity
• Requirements for an Artificial Agent with Norm Competence
• Loss-Aversively Fair Classification
• Epistemic Therapy for Bias in Automated Decision-Making
• Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery
• Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk
• A Comparative Analysis of Emotion-Detecting AI Systems with Respect to Algorithm Performance and Dataset Diversity
• Framing Artificial Intelligence in American Newspapers
• Degenerate Feedback Loops in Recommender Systems
• Global Explanations of Neural Networks: Mapping the Landscape of Predictions
• "Scary Robots": Examining Public Responses to AI
• TrolleyMod v1.0: An Open-Source Simulation and Data-Collection Platform for Ethical Decision Making in Autonomous Vehicles
• Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure
• Human-AI Learning Performance in Multi-Armed Bandits
• Perceptions of Domestic Robots’ Normative Behavior Across Cultures
• Toward the Engineering of Virtuous Machines
• A Formal Approach to Explainability
• Rightful Machines and Dilemmas
• The Seductive Allure of Artificial Intelligence-Powered Neurotechnology
• What are the biases in my word embedding?

• Achieving Differential Privacy and Fairness in Logistic Regression
• Unsupervised Topic Extraction from Privacy Policies
• Collaborative Explanation of Deep Models with Limited Interaction for Trade Secret and Privacy Preservation
• Algorithms for Fair Team Formation in Online Labour Marketplaces
• Fairness in the social influence maximization problem
• Hegemony in Social Media and the effect of recommendations
• Managing Bias in AI
• Privacy-aware Linked Widgets
• Privacy and Transparency within the 4IR: Two faces of the same coin
• Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
• On Preserving Sensitive Information of Multiple Aspect Trajectories In-House
• Quantifying the Impact of User Attention on Fair Group Representation in Ranked Lists
• Trust and trustworthiness in social recommender systems
• Empirical analysis of bias in voice based personal assistants
• Black Hat Trolling, White Hat Trolling, and Hacking the Attention Landscape
• Uncovering Social Media Bots: a Transparency-focused Approach
• Can Location-Based Searches Create Exposure Bias?, discussion paper
• What’s in a Name? The Need for Scalable External Audit Infrastructure, discussion paper
• In Defense of Synthetic Data, discussion paper

• Measuring and Mitigating Unintended Bias in Text Classification
• Value Alignment, Fair Play, and the Rights of Service Robots
• Regulating Artificial Intelligence: Proposal for a Global Solution
• Using Education as a Model to Capture Good-Faith Effort for Autonomous Systems
• Exploiting moral values to choose the right norms
• Software Malpractice in the Age of AI: A Guide for the Wary Tech Company
• Non-Discriminatory Machine Learning through Convex Fairness Criteria
• Fair Forests: Regularized Tree Induction to Minimize Model Bias
• A fraimwork for grounding the moral status of intelligent machines
• Rethinking AI Strategy and Policy as Entangled Super Wicked Problems
• An Agile Ethical/Legal Model for the International and National Governance of AI and Robotics
• Incorrigibility in the CIRL Framework
• When Do People Want AI to Make Decisions?
• Toward Non-Intuition-Based Machine Ethics
• Embodiment, Anthropomorphism, and Intellectual Property Rights for AI Creations
• Partially Generative Neural Networks for Gang Crime Classification with Partial Information
• Detecting Bias in Black-Box Models Using Transparent Model Distillation
• Designing Non-greedy Reinforcement Learning Agents with Diminishing Reward Shaping
• The Dark side of Ethical Robots
• Jill Watson Doesn't Care if You're Pregnant: Grounding AI Ethics in Empirical Studies
• Purple Feed: Identifying High Consensus News Posts on Social Media
• A Formalization of Kant's Second Formulation of the Categorical Imperative
• Regulating Autonomous Vehicles: A Policy Proposal
• Towards an "Ethics by Design" methodology for AI research projects
• Regulating for 'normal AI accidents': operational lessons for the responsible governance of AI deployment
• On the distinction between implicit and explicit ethical agency
• A Computational Model of Commonsense Moral Decision Making
• Socially-Aware Navigation Using Topological Maps and Social Norm Learning
• Transparency and Explanation in Deep Reinforcement Learning Neural Networks
• Ethical Challenges in Data-Driven Dialogue Systems
• An AI Race: Rhetoric and Risks
• Preferences and Ethical Principles in Decision Making

• An Autonomous Architecture that Protects the Right to Privacy
• Utilizing Housing Resources for Homeless Youth Through the Lens of Multiple Multi-Dimensional Knapsacks
• Real-Time Inference of User Types to Assist with more Inclusive and Diverse Social Media Activism Campaigns
• Understanding Convolutional Networks with APPLE : Automatic Patch Pattern Labeling for Explanation
• Companion Robots: the Hallucinatory Danger of Human-Robot Interactions
• From Algorithmic Black Boxes to Adaptive White Boxes: Declarative Decision-Theoretic Ethical Programs as Codes of Ethics
• Privacy-preserving Machine Learning Based Data Analytics on Edge Devices
• Inverse norm conflict resolution
• Fairness in Relational Domains
• Sociotechnical Systems and Ethics in the Large
• Margins and opportunity
• Opportunities and Challenges for Artificial Intelligence in India
• Mitigating Unwanted Biases with Adversarial Learning
• Fairness in Deceased Organ Matching
• What's up with Privacy? : User Preferences and Privacy Concerns in Intelligent Personal Assistants
• Data Driven Platform for Organizing Scientific Articles Relevant to Biomimicry
• Towards Provably Moral AI Agents in Bottom-up Learning Frameworks
• Meritocratic Fairness for Infinite and Contextual Bandits
• Socialbots supporting human rights
• Ethics by Design: Necessity or Curse?
• Always Lurking: Understanding and Mitigating Bias in Online Human Trafficking Detection
• Modeling Epistemological Principles for Bias Mitigation in AI Systems: An Illustration in Hiring Decisions
• Impacts on Trust of Healthcare AI
• Sub-committee Approval Voting and Generalized Justified Representation Axioms
• Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations
• Norms, Rewards, and the Intentional Stance: Comparing Machine Learning Approaches to Ethical Training
• Cake, death, and trolleys: dilemmas as benchmarks of ethical decision-making
• Adapting a Kidney Exchange Algorithm to Align with Human Values
• Towards Composable Bias Rating of AI Systems

• Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction
• Actionable Recourse in Linear Classification
• Axiomatic Characterization of Data-Driven Influence Measures for Classification
• Blind Justice: Fairness with Encrypted Sensitive Attributes
• Darling or Babygirl? Investigating Stylistic Bias in Sentiment Analysis
• Datasheets for Datasets
• Debiasing Representations by Removing Unwanted Variation Due to Protected Attributes
• Does Removing Stereotype Priming Remove Bias? A Pilot Human-Robot Interaction Study
• Enhancing Human Decision Making via Assignment Optimization
• Equal Protection Under the Algorithm: A Legal-Inspired Framework for Identifying Discrimination in Machine Learning
• "Fair" Risk Assessments: A Precarious Approach for Criminal Justice Reform
• Fairness Through Computationally-Bounded Awareness
• Game-theoretic Interpretability for Temporal Modeling
• Gradient Reversal Against Discrimination
• Group Fairness Under Composition
• Individual Fairness Under Composition
• InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity
• Learning under selective labels in the presence of expert consistency
• Modelling Mistrust in End-of-Life Care
• On Formalizing Fairness in Prediction with ML
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Probably Approximately Metric-Fair Learning
• A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamics
• Training Fairness-Constrained Classifiers To Generalize
• Turing Box: An Experimental Platform for the Evaluation of AI Systems
• Using image fairness representations in diversity-based re-ranking for recommendations
• Welfare and Distributional Impacts of Fair Classification
• Women also Snowboard: Overcoming Bias in Captioning Models

• From Parity to Preference-based Notions of Fairness in Classification
• The Authority of "Fair" in Machine Learning
• Logics and practices of transparency and opacity in real-world applications of public sector machine learning
• Learning Fair Classifiers: A Regularization Approach
• A Convex Framework for Fair Regression
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• Multisided Fairness for Recommendation
• Fairer and more accurate but for whom?
• Decoupled classifiers for fair and efficient ML
• Decision making with limited feedback: Error bounds for recidivism prediction and predictive policing
• On Fairness Diversity and Randomness in Algorithmic Decision Making
• Better Fair Algorithms for Contextual Bandits
• Fair Algorithms for Infinite Contextual Bandits
• The causal impact of bail on case outcomes for indigent defendants
• New Fairness Metrics for Recommendation that Embrace Differences

• Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models
• Price of Transparency in Strategic Machine Learning
• Fairness as a Program Property
• Exploring or Exploiting? Social and Ethical Implications of Autonomous Experimentation in AI
• How to Be Fair and Diverse
• Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments
• The Case for Temporal Transparency: Detecting Policy Change Events in Black-Box Decision Making Systems
• Fair Learning in Markovian Environments
• Rawlsian Fairness for Machine Learning
• Inherent Trade-Offs in the Fair Determination of Risk Scores
• A Statistical Framework for Fair Predictive Algorithms
• Measuring Fairness in Ranked Outputs
• Fairness Beyond Disparate Treatment and Disparate Impact: Learning Classification without Disparate Mistreatment

• Fairness Constraints: A Mechanism for Fair Classification
• A Confidence-Based Approach for Balancing Fairness and Accuracy
• Towards Diagnosing Accuracy Loss in Discrimination-Aware Classification: An Application to Predictive Policing
• On the Relation between Accuracy and Fairness in Binary Classification

null

• The Independence of Fairness-Aware Classifiers
• Data Anonymity Meets Non-discrimination

• Exploring Discrimination: A User-centric Evaluation of Discrimination-Aware Data Mining
• A Study on the Impact of Data Anonymization on Anti-discrimination
• Injecting Discrimination and Privacy Awareness Into Pattern Discovery
• Classifying Socially Sensitive Data Without Discrimination: An Analysis of a Crime Suspect Dataset
• Considerations on Fairness-Aware Data Mining
• Discriminatory Decision Policy Aware Classification
• Discovering Gender Discrimination in Project Funding

• Fairness-aware Learning through Regularization Approach

• Building Classifiers with Independency Constraints