{"total":89,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2106.05258","title":"Generative Models as a Data Source for Multiview Representation Learning","created":"2021-06-09","cited_by_count":104,"area":null},{"id":"2104.02821","title":"Towards Measuring Fairness in AI: the Casual Conversations Dataset","created":"2021-04-06","cited_by_count":80,"area":null},{"id":"2102.13004","title":"Towards Unbiased and Accurate Deferral to Multiple Experts","created":"2021-02-25","cited_by_count":72,"area":null},{"id":"2211.10946","title":"Normalizing Flows for Human Pose Anomaly Detection","created":"2022-11-20","cited_by_count":60,"area":null},{"id":"2108.02922","title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers","created":"2021-08-06","cited_by_count":49,"area":null},{"id":"2103.06076","title":"Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs","created":"2021-03-10","cited_by_count":48,"area":null},{"id":"2107.02823","title":"Deep Learning for Micro-expression Recognition: A Survey","created":"2021-07-06","cited_by_count":43,"area":null},{"id":"2401.07102","title":"Evolving Code with A Large Language Model","created":"2024-01-13","cited_by_count":43,"area":null},{"id":"2207.11345","title":"Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities","created":"2022-07-22","cited_by_count":28,"area":null},{"id":"2210.09943","title":"Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition","created":"2022-10-18","cited_by_count":26,"area":null},{"id":"2302.07159","title":"A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?","created":"2023-02-14","cited_by_count":25,"area":null},{"id":"2202.07603","title":"Fairness Indicators for Systematic Assessments of Visual Feature Extractors","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2401.10899","title":"Concrete Problems in AI Safety, Revisited","created":"2023-12-18","cited_by_count":22,"area":null},{"id":"2103.06172","title":"Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems","created":"2021-03-10","cited_by_count":21,"area":null},{"id":"2405.01820","title":"Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2102.06764","title":"Technical Challenges for Training Fair Neural Networks","created":"2021-02-12","cited_by_count":20,"area":null},{"id":"2111.04424","title":"A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication","created":"2021-10-18","cited_by_count":18,"area":null},{"id":"2301.03561","title":"Ancilia: Scalable Intelligent Video Surveillance for the Artificial Intelligence of Things","created":"2023-01-09","cited_by_count":17,"area":null},{"id":"2309.05148","title":"Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color","created":"2023-09-10","cited_by_count":17,"area":null},{"id":"2110.09839","title":"Measuring Hidden Bias within Face Recognition via Racial Phenotypes","created":"2021-10-19","cited_by_count":16,"area":null},{"id":"2302.01448","title":"Out of Context: Investigating the Bias and Fairness Concerns of \"Artificial Intelligence as a Service\"","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2306.06542","title":"Investigating Practices and Opportunities for Cross-functional Collaboration around AI Fairness in Industry Practice","created":"2023-06-10","cited_by_count":15,"area":null},{"id":"2404.12691","title":"Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?","created":"2024-04-19","cited_by_count":15,"area":null},{"id":"2207.11569","title":"Robots Enact Malignant Stereotypes","created":"2022-07-23","cited_by_count":14,"area":null},{"id":"2505.24214","title":"Benchmarking Foundation Models for Zero-Shot Biometric Tasks","created":"2025-05-30","cited_by_count":14,"area":"mllm"},{"id":"2208.05845","title":"Analyzing Fairness in Deepfake Detection With Massively Annotated Databases","created":"2022-08-11","cited_by_count":13,"area":null},{"id":"2112.07467","title":"AI Ethics Principles in Practice: Perspectives of Designers and Developers","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2304.05967","title":"Angler: Helping Machine Translation Practitioners Prioritize Model Improvements","created":"2023-04-12","cited_by_count":12,"area":null},{"id":"2202.03586","title":"Fair SA: Sensitivity Analysis for Fairness in Face Recognition","created":"2022-02-08","cited_by_count":11,"area":null},{"id":"2207.03444","title":"Fairness and Bias in Robot Learning","created":"2022-07-07","cited_by_count":10,"area":null},{"id":"2207.06084","title":"Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learning","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2305.00817","title":"Racial Bias within Face Recognition: A Survey","created":"2023-05-01","cited_by_count":9,"area":null},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2111.09137","title":"Two-Face: Adversarial Audit of Commercial Face Recognition Systems","created":"2021-11-17","cited_by_count":8,"area":null},{"id":"2201.07677","title":"Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows","created":"2022-01-19","cited_by_count":8,"area":null},{"id":"2101.11358","title":"Detecting discriminatory risk through data annotation based on Bayesian inferences","created":"2021-01-27","cited_by_count":7,"area":null},{"id":"2502.02309","title":"Review of Demographic Fairness in Face Recognition","created":"2025-02-04","cited_by_count":7,"area":null},{"id":"2111.08856","title":"Fairness Testing of Deep Image Classification with Adequacy Metrics","created":"2021-11-17","cited_by_count":6,"area":null},{"id":"2204.01108","title":"Adjusting for Bias with Procedural Data","created":"2022-04-03","cited_by_count":6,"area":null},{"id":"2208.07613","title":"Does lossy image compression affect racial bias within face recognition?","created":"2022-08-16","cited_by_count":5,"area":null},{"id":"2211.11835","title":"Fairness Increases Adversarial Vulnerability","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2406.11855","title":"Law and the Emerging Political Economy of Algorithmic Audits","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2111.03687","title":"AI and Blackness: Towards moving beyond bias and representation","created":"2021-11-05","cited_by_count":4,"area":null},{"id":"2201.11197","title":"Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Images","created":"2022-01-26","cited_by_count":3,"area":null},{"id":"2207.05727","title":"Enhancing Fairness of Visual Attribute Predictors","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2210.04491","title":"A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2303.15592","title":"Uncovering Bias in Personal Informatics","created":"2023-03-27","cited_by_count":3,"area":null},{"id":"2304.04029","title":"Bipol: A Novel Multi-Axes Bias Evaluation Metric with Explainability for NLP","created":"2023-04-08","cited_by_count":3,"area":null},{"id":"2304.09826","title":"Fairness in AI and Its Long-Term Implications on Society","created":"2023-04-16","cited_by_count":3,"area":null},{"id":"2311.03567","title":"Inclusive Portraits: Race-Aware Human-in-the-Loop Technology","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2311.17259","title":"SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2404.16255","title":"Enhancing Privacy in Face Analytics Using Fully Homomorphic Encryption","created":"2024-04-24","cited_by_count":3,"area":null},{"id":"2407.15810","title":"Breaking the Global North Stereotype: A Global South-centric Benchmark Dataset for Auditing and Mitigating Biases in Facial Recognition Systems","created":"2024-07-22","cited_by_count":3,"area":null},{"id":"2502.09460","title":"Metamorphic Testing for Pose Estimation Systems","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2112.11193","title":"There is an elephant in the room: Towards a critique on the use of fairness in biometrics","created":"2021-12-16","cited_by_count":2,"area":null},{"id":"2207.12319","title":"OpenFilter: A Framework to Democratize Research Access to Social Media AR Filters","created":"2022-07-19","cited_by_count":2,"area":null},{"id":"2301.12139","title":"Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets","created":"2023-01-28","cited_by_count":2,"area":null},{"id":"2303.08177","title":"The Equitable AI Research Roundtable (EARR): Towards Community-Based Decision Making in Responsible AI Development","created":"2023-03-14","cited_by_count":2,"area":null},{"id":"2311.06145","title":"An Evaluation of Forensic Facial Recognition","created":"2023-11-10","cited_by_count":2,"area":null},{"id":"2404.04838","title":"Data Bias According to Bipol: Men are Naturally Right and It is the Role of Women to Follow Their Lead","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2408.10239","title":"A Conceptual Framework for Ethical Evaluation of Machine Learning Systems","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2410.10850","title":"On the Reliability of Large Language Models to Misinformed and Demographically-Informed Prompts","created":"2024-10-06","cited_by_count":2,"area":null},{"id":"2502.17748","title":"FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk","created":"2025-02-25","cited_by_count":2,"area":null},{"id":"2111.03984","title":"Proposing an Interactive Audit Pipeline for Visual Privacy Research","created":"2021-11-07","cited_by_count":1,"area":null},{"id":"2111.04439","title":"Addressing Privacy Threats from Machine Learning","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2112.09326","title":"Cinderella's shoe won't fit Soundarya: An audit of facial processing tools on Indian faces","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2508.04939","title":"I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations","created":"2025-08-06","cited_by_count":1,"area":"lr"},{"id":"2508.14170","title":"Comparing energy consumption and accuracy in text classification inference","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2101.11587","title":"The Work of Art in an Age of Mechanical Generation","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2102.08004","title":"A Mental Trespass? Unveiling Truth, Exposing Thoughts and Threatening Civil Liberties with Non-Invasive AI Lie Detection","created":"2021-02-16","cited_by_count":0,"area":null},{"id":"2109.02351","title":"F3: Fair and Federated Face Attribute Classification with Heterogeneous Data","created":"2021-09-06","cited_by_count":0,"area":null},{"id":"2206.03583","title":"Contributor-Aware Defenses Against Adversarial Backdoor Attacks","created":"2022-05-28","cited_by_count":0,"area":null},{"id":"2212.11670","title":"Evaluation for Change","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2302.03774","title":"AI and Core Electoral Processes: Mapping the Horizons","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2306.10919","title":"Fairness Index Measures to Evaluate Bias in Biometric Recognition","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2402.13771","title":"Mask-up: Investigating Biases in Face Re-identification for Masked Faces","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2410.12148","title":"Facing Identity: The Formation and Performance of Identity via Face-Based Artificial Intelligence Technologies","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2503.14138","title":"Exploring Disparity-Accuracy Trade-offs in Face Recognition Systems: The Role of Datasets, Architectures, and Loss Functions","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2503.20108","title":"Peepers & Pixels: Human Recognition Accuracy on Low Resolution Faces","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2510.17873","title":"Auditing and Mitigating Bias in Gender Classification Algorithms: A Data-Centric Approach","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.20482","title":"Reliable and Reproducible Demographic Inference for Fairness in Face Analysis","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.03199","title":"Does Head Pose Correction Improve Biometric Facial Recognition?","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.08981","title":"Mitigating Bias with Words: Inducing Demographic Ambiguity in Face Recognition Templates by Text Encoding","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2603.02420","title":"Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2604.20805","title":"Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2608.28802","title":"A Large-scale Evaluation of Text-guided Models for Facial Editing","created":"2026-08-28","cited_by_count":0,"area":null}],"next_cursor":null}