{"total":52,"rows":[{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139,"area":null},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2305.11844","title":"AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia","created":"2023-05-19","cited_by_count":54,"area":null},{"id":"2304.09991","title":"Supporting Human-AI Collaboration in Auditing LLMs with LLMs","created":"2023-04-19","cited_by_count":46,"area":null},{"id":"2304.10619","title":"\"HOT\" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media","created":"2023-04-20","cited_by_count":45,"area":"safety"},{"id":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","cited_by_count":30,"area":null},{"id":"2311.09743","title":"Capturing Perspectives of Crowdsourced Annotators in Subjective Learning Tasks","created":"2023-11-16","cited_by_count":29,"area":null},{"id":"2402.15350","title":"Farsight: Fostering Responsible AI Awareness During AI Application Prototyping","created":"2024-02-23","cited_by_count":28,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2302.06503","title":"Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2207.09899","title":"Labeling instructions matter in biomedical image analysis","created":"2022-07-20","cited_by_count":20,"area":null},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"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":"2211.12703","title":"Subgroup Robustness Grows On Trees: An Empirical Baseline Investigation","created":"2022-11-23","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":"2311.05074","title":"GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives","created":"2023-11-09","cited_by_count":16,"area":"safety"},{"id":"2402.01787","title":"Harm Amplification in Text-to-Image Models","created":"2024-02-01","cited_by_count":15,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"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":"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":"2404.10857","title":"D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation","created":"2024-04-16","cited_by_count":11,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2402.06811","title":"Discipline and Label: A WEIRD Genealogy and Social Theory of Data Annotation","created":"2024-02-09","cited_by_count":8,"area":null},{"id":"2506.16393","title":"From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling","created":"2025-06-19","cited_by_count":8,"area":null},{"id":"2210.07415","title":"Noise Audits Improve Moral Foundation Classification","created":"2022-10-13","cited_by_count":7,"area":null},{"id":"2402.02249","title":"Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget","created":"2024-02-03","cited_by_count":7,"area":null},{"id":"2303.17176","title":"A View From Somewhere: Human-Centric Face Representations","created":"2023-03-30","cited_by_count":6,"area":null},{"id":"2406.05902","title":"Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human Feedback","created":"2024-06-09","cited_by_count":6,"area":"alignment"},{"id":"2204.09852","title":"The Risks of Machine Learning Systems","created":"2022-04-21","cited_by_count":5,"area":null},{"id":"2308.08656","title":"Flickr Africa: Examining Geo-Diversity in Large-Scale, Human-Centric Visual Data","created":"2023-08-16","cited_by_count":5,"area":null},{"id":"2410.09416","title":"Can Vision-Language Models Replace Human Annotators: A Case Study with CelebA Dataset","created":"2024-10-12","cited_by_count":5,"area":"mllm"},{"id":"2211.11206","title":"Cultural Re-contextualization of Fairness Research in Language Technologies in India","created":"2022-11-21","cited_by_count":4,"area":null},{"id":"2311.04345","title":"A Taxonomy of Rater Disagreements: Surveying Challenges & Opportunities from the Perspective of Annotating Online Toxicity","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2402.04420","title":"Measuring Machine Learning Harms from Stereotypes Requires Understanding Who Is Harmed by Which Errors in What Ways","created":"2024-02-06","cited_by_count":4,"area":null},{"id":"2410.17032","title":"Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2511.05613","title":"Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations","created":"2025-11-06","cited_by_count":4,"area":null},{"id":"2310.14572","title":"Unveiling the Multi-Annotation Process: Examining the Influence of Annotation Quantity and Instance Difficulty on Model Performance","created":"2023-10-23","cited_by_count":3,"area":null},{"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":"2605.07084","title":"Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2501.16507","title":"Characterizing Network Structure of Anti-Trans Actors on TikTok","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2605.30808","title":"Differentially Private Preference Data Synthesis for Large Language Model Alignment","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2310.09314","title":"Eliciting Model Steering Interactions from Users via Data and Visual Design Probes","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2310.18303","title":"Socially Cognizant Robotics for a Technology Enhanced Society","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2508.10071","title":"Advancing Data Equity: Practitioner Responsibility and Accountability in NLP Data Practices","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.05864","title":"On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2604.08425","title":"Learning Who Disagrees: Demographic Importance Weighting for Modeling Annotator Distributions with DiADEM","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.16654","title":"IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.09955","title":"Beyond Majority Voting: Agreement-Based Clustering to Model Annotator Perspectives in Subjective NLP Tasks","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.26397","title":"Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2606.19151","title":"The Market in the Model: Latent Diffusion as Neural Economy","created":"2026-06-17","cited_by_count":0,"area":"diffusion"},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}