{"total":116,"rows":[{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293,"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":"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":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449,"area":null},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349,"area":null},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218,"area":null},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180,"area":null},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118,"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":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104,"area":"mllm"},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96,"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":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80,"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":"2205.04610","title":"Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation","created":"2022-05-10","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":"2403.07857","title":"Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias","created":"2024-03-12","cited_by_count":55,"area":null},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54,"area":null},{"id":"2201.10474","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","created":"2022-01-25","cited_by_count":53,"area":null},{"id":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51,"area":null},{"id":"2301.02560","title":"GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition","created":"2023-01-05","cited_by_count":50,"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":"2204.14256","title":"Handling and Presenting Harmful Text in NLP Research","created":"2022-04-29","cited_by_count":43,"area":null},{"id":"2205.03295","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38,"area":null},{"id":"2206.07173","title":"Measuring Representational Harms in Image Captioning","created":"2022-06-14","cited_by_count":36,"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":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","cited_by_count":32,"area":null},{"id":"2103.03399","title":"Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data","created":"2021-03-05","cited_by_count":31,"area":null},{"id":"2109.07437","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","created":"2021-09-15","cited_by_count":26,"area":null},{"id":"2205.04460","title":"Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches","created":"2022-05-06","cited_by_count":25,"area":null},{"id":"2103.00755","title":"Adaptive Sampling for Minimax Fair Classification","created":"2021-03-01","cited_by_count":24,"area":null},{"id":"2110.09253","title":"A Sociotechnical View of Algorithmic Fairness","created":"2021-09-27","cited_by_count":24,"area":null},{"id":"2105.02091","title":"When Fair Ranking Meets Uncertain Inference","created":"2021-05-05","cited_by_count":22,"area":null},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22,"area":null},{"id":"2210.11924","title":"Men Also Do Laundry: Multi-Attribute Bias Amplification","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2401.07348","title":"Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity","created":"2024-01-14","cited_by_count":21,"area":null},{"id":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"id":"2105.12936","title":"Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence","created":"2021-05-27","cited_by_count":19,"area":null},{"id":"2212.05129","title":"Measuring Data","created":"2022-12-09","cited_by_count":18,"area":null},{"id":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","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":"2202.11833","title":"Near Perfect GAN Inversion","created":"2022-02-23","cited_by_count":15,"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":"2105.12754","title":"Computer Vision and Conflicting Values: Describing People with Automated Alt Text","created":"2021-05-26","cited_by_count":14,"area":null},{"id":"2207.11569","title":"Robots Enact Malignant Stereotypes","created":"2022-07-23","cited_by_count":14,"area":null},{"id":"2406.12844","title":"Synergizing Foundation Models and Federated Learning: A Survey","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2211.07907","title":"MMD-B-Fair: Learning Fair Representations with Statistical Testing","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2201.10066","title":"Documenting Geographically and Contextually Diverse Data Sources: The BigScience Catalogue of Language Data and Resources","created":"2022-01-25","cited_by_count":11,"area":null},{"id":"2305.09072","title":"Skin Deep: Investigating Subjectivity in Skin Tone Annotations for Computer Vision Benchmark Datasets","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2502.19190","title":"Provocations from the Humanities for Generative AI Research","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2506.05104","title":"Survey on the Evaluation of Generative Models in Music","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2108.08874","title":"Towards A Fairer Landmark Recognition Dataset","created":"2021-08-19","cited_by_count":9,"area":null},{"id":"2407.14259","title":"Voices in a Crowd: Searching for Clusters of Unique Perspectives","created":"2024-07-19","cited_by_count":9,"area":null},{"id":"2502.00198","title":"Fairshare Data Pricing via Data Valuation for Large Language Models","created":"2025-01-31","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":"2203.09911","title":"Why we need biased AI -- How including cognitive and ethical machine biases can enhance AI systems","created":"2022-03-18","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":"2206.13304","title":"PARTICUL: Part Identification with Confidence measure using Unsupervised Learning","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2207.09960","title":"Measuring and signing fairness as performance under multiple stakeholder distributions","created":"2022-07-20","cited_by_count":6,"area":null},{"id":"2208.01157","title":"Global Performance Disparities Between English-Language Accents in Automatic Speech Recognition","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2303.07242","title":"Can Workers Meaningfully Consent to Workplace Wellbeing Technologies?","created":"2023-03-13","cited_by_count":6,"area":null},{"id":"2405.01286","title":"Data Feminism for AI","created":"2024-05-02","cited_by_count":6,"area":null},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","cited_by_count":5,"area":"safety"},{"id":"2302.08406","title":"Entity Aware Modelling: A Survey","created":"2023-02-16","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":"2401.15270","title":"SimFair: Physics-Guided Fairness-Aware Learning with Simulation Models","created":"2024-01-27","cited_by_count":4,"area":null},{"id":"2407.12793","title":"Data Collection and Labeling Techniques for Machine Learning","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2407.16875","title":"PathwayBench: Assessing Routability of Pedestrian Pathway Networks Inferred from Multi-City Imagery","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2302.14534","title":"Spacerini: Plug-and-play Search Engines with Pyserini and Hugging Face","created":"2023-02-28","cited_by_count":3,"area":null},{"id":"2303.02323","title":"APE: An Open and Shared Annotated Dataset for Learning Urban Pedestrian Path Networks","created":"2023-03-04","cited_by_count":3,"area":null},{"id":"2408.15244","title":"Misrepresented Technological Solutions in Imagined Futures: The Origins and Dangers of AI Hype in the Research Community","created":"2024-08-08","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":"2509.23482","title":"GeoBS: Information-Theoretic Quantification of Geographic Bias in AI Models","created":"2025-09-27","cited_by_count":3,"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":"2209.00746","title":"MIME: Minority Inclusion for Majority Group Enhancement of AI Performance","created":"2022-09-01","cited_by_count":2,"area":null},{"id":"2210.07188","title":"ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution","created":"2022-10-13","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},{"id":"2406.06407","title":"A Taxonomy of Challenges to Curating Fair Datasets","created":"2024-06-10","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":"2408.11160","title":"Statistical Challenges with Dataset Construction: Why You Will Never Have Enough Images","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2408.12665","title":"Fairness-Aware Streaming Feature Selection with Causal Graphs","created":"2024-08-17","cited_by_count":2,"area":null},{"id":"2408.12778","title":"Data-Centric Approach to Constrained Machine Learning: A Case Study on Conway's Game of Life","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2410.09086","title":"AI in Archival Science -- A Systematic Review","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2503.05721","title":"What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets","created":"2025-02-17","cited_by_count":2,"area":"safety"},{"id":"2508.18288","title":"Toward Responsible ASR for African American English Speakers: A Scoping Review of Bias and Equity in Speech Technology","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2509.15759","title":"On Optimal Steering to Achieve Exact Fairness","created":"2025-09-19","cited_by_count":2,"area":"mechinterp"},{"id":"2602.11318","title":"The Consensus Trap: Dissecting Subjectivity and the \"Ground Truth\" Illusion in Data Annotation","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2208.02670","title":"Development and Validation of ML-DQA -- a Machine Learning Data Quality Assurance Framework for Healthcare","created":"2022-08-04","cited_by_count":1,"area":null},{"id":"2210.09232","title":"Confound-leakage: Confound Removal in Machine Learning Leads to Leakage","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2304.01890","title":"Sociocultural knowledge is needed for selection of shots in hate speech detection tasks","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2311.14381","title":"Potential Societal Biases of ChatGPT in Higher Education: A Scoping Review","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2412.16355","title":"Social Science Is Necessary for Operationalizing Socially Responsible Foundation Models","created":"2024-12-20","cited_by_count":1,"area":null},{"id":"2505.03025","title":"A Typology of Synthetic Datasets for Dialogue Processing in Clinical Contexts","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2506.02071","title":"AI Data Development: A Scorecard for the System Card Framework","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2604.20357","title":"SignDATA: Data Pipeline for Sign Language Translation","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.04127","title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","created":"2026-05-05","cited_by_count":1,"area":"synth"}],"next_cursor":"100"}