{"total":69,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773,"area":null},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100,"area":"synth"},{"id":"2309.07034","title":"Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting","created":"2023-09-13","cited_by_count":81,"area":null},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"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":"2306.11559","title":"The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics","created":"2023-06-20","cited_by_count":46,"area":null},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45,"area":null},{"id":"2304.12397","title":"On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research","created":"2023-04-24","cited_by_count":44,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2405.05860","title":"The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels","created":"2024-05-09","cited_by_count":38,"area":null},{"id":"2502.20897","title":"Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions","created":"2025-02-28","cited_by_count":33,"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":"2305.09073","title":"Consensus and Subjectivity of Skin Tone Annotation for ML Fairness","created":"2023-05-16","cited_by_count":22,"area":null},{"id":"2404.01651","title":"NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps","created":"2024-04-02","cited_by_count":20,"area":null},{"id":"2307.10221","title":"`It is currently hodgepodge'': Examining AI/ML Practitioners' Challenges during Co-production of Responsible AI Values","created":"2023-07-14","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":"2405.04457","title":"Towards Geographic Inclusion in the Evaluation of Text-to-Image Models","created":"2024-05-07","cited_by_count":16,"area":null},{"id":"2406.11757","title":"STAR: SocioTechnical Approach to Red Teaming Language Models","created":"2024-06-17","cited_by_count":13,"area":"safety"},{"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":"2410.03448","title":"\"Cold, Calculated, and Condescending\": How AI Identifies and Explains Ableism Compared to Disabled People","created":"2024-10-04","cited_by_count":10,"area":null},{"id":"2408.08411","title":"Rater Cohesion and Quality from a Vicarious Perspective","created":"2024-08-15","cited_by_count":8,"area":null},{"id":"2410.03543","title":"Re-examining Sexism and Misogyny Classification with Annotator Attitudes","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2311.00203","title":"Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2401.14322","title":"Generalized People Diversity: Learning a Human Perception-Aligned Diversity Representation for People Images","created":"2024-01-25","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":"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":"2505.10309","title":"A large-scale evaluation of commonsense knowledge in humans and large language models","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2212.09409","title":"Aggregating Soft Labels from Crowd Annotations Improves Uncertainty Estimation Under Distribution Shift","created":"2022-12-19","cited_by_count":3,"area":null},{"id":"2409.13725","title":"Identity-related Speech Suppression in Generative AI Content Moderation","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2411.04090","title":"A Collaborative Content Moderation Framework for Toxicity Detection based on Conformalized Estimates of Annotation Disagreement","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2502.02696","title":"How Inclusively do LMs Perceive Social and Moral Norms?","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2509.06704","title":"Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2603.05801","title":"Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2406.06587","title":"TouchAI: Exploring human-AI perceptual alignment in touch through language model representations","created":"2024-06-05","cited_by_count":2,"area":"alignment"},{"id":"2411.08135","title":"On the Role of Speech Data in Reducing Toxicity Detection Bias","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2502.09004","title":"Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speech","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2503.16505","title":"Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"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":"2210.06351","title":"A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter","created":"2022-10-07","cited_by_count":1,"area":"safety"},{"id":"2301.09902","title":"Investigating Labeler Bias in Face Annotation for Machine Learning","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2307.06513","title":"Leveraging Contextual Counterfactuals Toward Belief Calibration","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2310.02357","title":"On the definition of toxicity in NLP","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2403.05576","title":"Understanding Subjectivity through the Lens of Motivational Context in Model-Generated Image Satisfaction","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2406.10590","title":"LLM-Mediated Domain-Specific Voice Agents: The Case of TextileBot","created":"2024-06-15","cited_by_count":1,"area":"agents"},{"id":"2408.01455","title":"Ontology of Belief Diversity: A Community-Based Epistemological Approach","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2409.17130","title":"Assessing the Level of Toxicity Against Distinct Groups in Bangla Social Media Comments: A Comprehensive Investigation","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.14894","title":"Soft-Label Integration for Robust Toxicity Classification","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2506.08593","title":"Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2507.02819","title":"Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2507.05455","title":"ModelCitizens: Representing Community Voices in Online Safety","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2305.19864","title":"Designing Closed-Loop Models for Task Allocation","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2503.16072","title":"Toxicity Is a Property of Communicative Events: A Contextual Stress Measurement Framework for NLP","created":"2025-03-20","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":"2510.01976","title":"Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2512.00673","title":"A Comparison of Human and ChatGPT Classification Performance on Complex Social Media Data","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2602.06055","title":"Are we chasing ghosts? Quantifying unattributable polarization, and attributing the rest to annotator groups","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","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":"2606.07123","title":"Learning Perspectivist Social Meaning via Demographic-Conditioned Fusion Embeddings","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.00873","title":"How Ethos and Pathos Appeals Resonate in Reader Interpretations of Social Media Messages","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.24898","title":"Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.30842","title":"Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2610.02631","title":"Designing the Future of User Feedback for Generative AI","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12701","title":"Activating the Annotator: Operationalising Lived Experience in Data Annotation","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}