{"total":138,"rows":[{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295,"area":null},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530,"area":null},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492,"area":null},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203,"area":null},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172,"area":"diffusion"},{"id":"2204.01075","title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","created":"2022-04-03","cited_by_count":171,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117,"area":null},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108,"area":null},{"id":"2108.04308","title":"Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development","created":"2021-08-09","cited_by_count":85,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73,"area":null},{"id":"2112.05675","title":"Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Support","created":"2021-12-10","cited_by_count":63,"area":null},{"id":"2206.08931","title":"CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation","created":"2022-06-09","cited_by_count":59,"area":null},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2307.05532","title":"Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators","created":"2023-07-08","cited_by_count":56,"area":"alignment"},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54,"area":null},{"id":"2112.04554","title":"Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation","created":"2021-12-08","cited_by_count":52,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2202.05338","title":"Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning","created":"2022-02-10","cited_by_count":48,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","cited_by_count":46,"area":null},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2304.14749","title":"Understanding accountability in algorithmic supply chains","created":"2023-04-28","cited_by_count":40,"area":null},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38,"area":null},{"id":"2307.02192","title":"The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification","created":"2023-07-05","cited_by_count":34,"area":null},{"id":"2206.03216","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","created":"2022-05-04","cited_by_count":33,"area":null},{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2206.14983","title":"A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms","created":"2022-06-30","cited_by_count":30,"area":null},{"id":"2206.02923","title":"Understanding Machine Learning Practitioners' Data Documentation Perceptions, Needs, Challenges, and Desiderata","created":"2022-06-06","cited_by_count":28,"area":null},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2108.07374","title":"Reusable Templates and Guides For Documenting Datasets and Models for Natural Language Processing and Generation: A Case Study of the HuggingFace and GEM Data and Model Cards","created":"2021-08-16","cited_by_count":24,"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":"2202.13028","title":"Healthsheet: Development of a Transparency Artifact for Health Datasets","created":"2022-02-26","cited_by_count":23,"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":"2209.04963","title":"Responsible AI Pattern Catalogue: A Collection of Best Practices for AI Governance and Engineering","created":"2022-09-12","cited_by_count":20,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2401.08053","title":"SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation","created":"2024-01-16","cited_by_count":19,"area":null},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18,"area":null},{"id":"2306.09562","title":"Reproducibility in NLP: What Have We Learned from the Checklist?","created":"2023-06-16","cited_by_count":18,"area":null},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2304.10655","title":"The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions","created":"2023-04-20","cited_by_count":17,"area":null},{"id":"2405.08209","title":"Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp","created":"2024-05-13","cited_by_count":15,"area":null},{"id":"2107.03844","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","created":"2021-07-08","cited_by_count":13,"area":null},{"id":"2205.04525","title":"Towards a multi-stakeholder value-based assessment framework for algorithmic systems","created":"2022-05-09","cited_by_count":12,"area":null},{"id":"2207.02848","title":"A domain-specific language for describing machine learning datasets","created":"2022-07-05","cited_by_count":12,"area":null},{"id":"2105.08867","title":"AI and Ethics -- Operationalising Responsible AI","created":"2021-05-19","cited_by_count":11,"area":null},{"id":"2110.14336","title":"Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2309.12327","title":"Ground Truth Or Dare: Factors Affecting The Creation Of Medical Datasets For Training AI","created":"2023-08-12","cited_by_count":11,"area":null},{"id":"2402.05160","title":"What's documented in AI? Systematic Analysis of 32K AI Model Cards","created":"2024-02-07","cited_by_count":11,"area":null},{"id":"2206.03275","title":"The Algorithmic Imprint","created":"2022-06-03","cited_by_count":10,"area":null},{"id":"2406.18211","title":"AI Cards: Towards an Applied Framework for Machine-Readable AI and Risk Documentation Inspired by the EU AI Act","created":"2024-06-26","cited_by_count":10,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2203.08594","title":"Towards a Roadmap on Software Engineering for Responsible AI","created":"2022-03-09","cited_by_count":9,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2501.10727","title":"In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2202.12603","title":"Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASR","created":"2022-02-25","cited_by_count":7,"area":null},{"id":"2205.05192","title":"Social Inclusion in Curated Contexts: Insights from Museum Practices","created":"2022-05-10","cited_by_count":7,"area":null},{"id":"2210.00859","title":"Requirements Engineering for Machine Learning: A Review and Reflection","created":"2022-10-03","cited_by_count":7,"area":null},{"id":"2301.05154","title":"Mephisto: A Framework for Portable, Reproducible, and Iterative Crowdsourcing","created":"2023-01-12","cited_by_count":7,"area":null},{"id":"2312.06153","title":"Open Datasheets: Machine-readable Documentation for Open Datasets and Responsible AI Assessments","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2509.22367","title":"What Is The Political Content in LLMs' Pre- and Post-Training Data?","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2402.06353","title":"Copycats: the many lives of a publicly available medical imaging dataset","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2506.01789","title":"Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2203.08007","title":"Data Smells in Public Datasets","created":"2022-03-15","cited_by_count":5,"area":null},{"id":"2303.05500","title":"Users are the North Star for AI Transparency","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2311.05792","title":"Is a Seat at the Table Enough? Engaging Teachers and Students in Dataset Specification for ML in Education","created":"2023-11-09","cited_by_count":5,"area":null},{"id":"2312.14977","title":"Diffusion Models for Generative Artificial Intelligence: An Introduction for Applied Mathematicians","created":"2023-12-21","cited_by_count":5,"area":"diffusion"},{"id":"2404.06717","title":"Racial/Ethnic Categories in AI and Algorithmic Fairness: Why They Matter and What They Represent","created":"2024-04-10","cited_by_count":5,"area":null},{"id":"2408.09196","title":"Maintainability Challenges in ML: A Systematic Literature Review","created":"2024-08-17","cited_by_count":5,"area":null},{"id":"2504.12562","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2505.15553","title":"Social Bias in Popular Question-Answering Benchmarks","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2102.07574","title":"Machine Learning Model Development from a Software Engineering Perspective: A Systematic Literature Review","created":"2021-02-15","cited_by_count":4,"area":null},{"id":"2202.04530","title":"An Exploration of Multicalibration Uniform Convergence Bounds","created":"2022-02-09","cited_by_count":4,"area":null},{"id":"2204.02842","title":"Open-Source Tools for Behavioral Video Analysis: Setup, Methods, and Development","created":"2022-04-06","cited_by_count":4,"area":null},{"id":"2205.05661","title":"How Platform-User Power Relations Shape Algorithmic Accountability: A Case Study of Instant Loan Platforms and Financially Stressed Users in India","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2303.05947","title":"Automotive Perception Software Development: An Empirical Investigation into Data, Annotation, and Ecosystem Challenges","created":"2023-03-10","cited_by_count":4,"area":null},{"id":"2303.15219","title":"Knowing the Distance: Understanding the Gap Between Synthetic and Real Data For Face Parsing","created":"2023-03-27","cited_by_count":4,"area":null},{"id":"2305.17465","title":"Optimization's Neglected Normative Commitments","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2407.17395","title":"The Costs of Pretending That There Are Data-Generating Probability Distributions in the Social World","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2105.06370","title":"Providing Assurance and Scrutability on Shared Data and Machine Learning Models with Verifiable Credentials","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2304.07296","title":"MLOps Spanning Whole Machine Learning Life Cycle: A Survey","created":"2023-04-13","cited_by_count":3,"area":null},{"id":"2309.11691","title":"RAI4IoE: Responsible AI for Enabling the Internet of Energy","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2311.09443","title":"Subtle Misogyny Detection and Mitigation: An Expert-Annotated Dataset","created":"2023-11-15","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":"2406.14758","title":"Compliance Cards: Automated EU AI Act Compliance Analyses amidst a Complex AI Supply Chain","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2501.10909","title":"Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition","created":"2025-01-19","cited_by_count":3,"area":null},{"id":"2503.13463","title":"Completeness of Datasets Documentation on ML/AI repositories: an Empirical Investigation","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2508.08804","title":"TechOps: Technical Documentation Templates for the AI Act","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2111.02034","title":"Building Legal Datasets","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2203.12697","title":"What is Software Quality for AI Engineers? Towards a Thinning of the Fog","created":"2022-03-23","cited_by_count":2,"area":null},{"id":"2204.09622","title":"A Brief Guide to Designing and Evaluating Human-Centered Interactive Machine Learning","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2206.01326","title":"Improving Fairness in Large-Scale Object Recognition by CrowdSourced Demographic Information","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2310.15848","title":"On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms","created":"2023-10-24","cited_by_count":2,"area":null}],"next_cursor":"100"}