{"total":90,"rows":[{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169,"area":null},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133,"area":"alignment"},{"id":"2402.05133","title":"Personalized Language Modeling from Personalized Human Feedback","created":"2024-02-06","cited_by_count":132,"area":"alignment"},{"id":"2309.07034","title":"Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting","created":"2023-09-13","cited_by_count":81,"area":null},{"id":"2410.13788","title":"Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions","created":"2024-10-17","cited_by_count":76,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2407.02996","title":"Are Large Language Models Consistent over Value-laden Questions?","created":"2024-07-03","cited_by_count":58,"area":null},{"id":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49,"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":"2408.15549","title":"WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback","created":"2024-08-28","cited_by_count":31,"area":"alignment"},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2401.14698","title":"Under the Surface: Tracking the Artifactuality of LLM-Generated Data","created":"2024-01-26","cited_by_count":24,"area":"synth"},{"id":"2603.25001","title":"Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation","created":"2026-03-26","cited_by_count":24,"area":"lr"},{"id":"2407.14916","title":"Improving Context-Aware Preference Modeling for Language Models","created":"2024-07-20","cited_by_count":22,"area":"alignment"},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2510.05931","title":"Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2601.09065","title":"Beyond Consensus: Perspectivist Modeling and Evaluation of Annotator Disagreement in NLP","created":"2026-01-14","cited_by_count":13,"area":null},{"id":"2603.06865","title":"Counting on Consensus: Selecting the Right Inter-annotator Agreement Metric for NLP Annotation and Evaluation","created":"2026-03-06","cited_by_count":13,"area":null},{"id":"2404.11826","title":"AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence","created":"2024-04-18","cited_by_count":12,"area":null},{"id":"2505.24846","title":"MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning","created":"2025-05-30","cited_by_count":11,"area":"alignment"},{"id":"2508.02853","title":"Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives","created":"2025-08-04","cited_by_count":10,"area":"moe"},{"id":"2403.02268","title":"Subjective $\\textit{Isms}$? On the Danger of Conflating Hate and Offence in Abusive Language Detection","created":"2024-03-04","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":"2404.02340","title":"Corpus Considerations for Annotator Modeling and Scaling","created":"2024-04-02","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":"2503.17338","title":"Capturing Individual Human Preferences with Reward Features","created":"2025-03-21","cited_by_count":8,"area":"alignment"},{"id":"2310.15288","title":"Active teacher selection for reward learning","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2410.23448","title":"Venire: A Machine Learning-Guided Panel Review System for Community Content Moderation","created":"2024-10-30","cited_by_count":7,"area":null},{"id":"2411.08977","title":"Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness","created":"2024-11-13","cited_by_count":7,"area":null},{"id":"2507.18890","title":"NUTMEG: Separating Signal From Noise in Annotator Disagreement","created":"2025-07-25","cited_by_count":7,"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":"2505.24712","title":"HESEIA: A community-based dataset for evaluating social biases in large language models, co-designed in real school settings in Latin America","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2601.13024","title":"Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2404.13307","title":"Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions","created":"2024-04-20","cited_by_count":5,"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":"2311.05020","title":"First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2503.18247","title":"AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2506.20209","title":"Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2601.11459","title":"Interactive Narrative Analytics: Bridging Computational Narrative Extraction and Human Sensemaking","created":"2026-01-16","cited_by_count":4,"area":null},{"id":"2404.12933","title":"Cross-cultural Inspiration Detection and Analysis in Real and LLM-generated Social Media Data","created":"2024-04-19","cited_by_count":3,"area":null},{"id":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2410.12217","title":"Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree","created":"2024-10-16","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":"2412.11745","title":"Beyond Dataset Creation: Critical View of Annotation Variation and Bias Probing of a Dataset for Online Radical Content Detection","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2502.08266","title":"Dealing with Annotator Disagreement in Hate Speech Classification","created":"2025-02-12","cited_by_count":3,"area":"safety"},{"id":"2503.00610","title":"Multimodal Large Language Models Predict Urban Safety Perception but Encode Non-Neutral Demographic Priors","created":"2025-03-01","cited_by_count":3,"area":"mllm"},{"id":"2507.05010","title":"Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","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":"2605.02122","title":"STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2410.17271","title":"Rules, Cases, and Reasoning: Positivist Legal Theory as a Framework for Pluralistic AI Alignment","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2412.04942","title":"A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities","created":"2024-12-06","cited_by_count":2,"area":null},{"id":"2506.02326","title":"Something Just Like TRuST : Toxicity Recognition of Span and Target","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2509.22699","title":"Are you sure? Measuring models bias in content moderation through uncertainty","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2512.09066","title":"ORCA: Open-ended Response Correctness Assessment for Audio Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2407.11933","title":"Fairness-Aware Multi-Group Target Detection in Online Discussion","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2410.19812","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2501.06826","title":"Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication","created":"2025-01-12","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":"2507.05455","title":"ModelCitizens: Representing Community Voices in Online Safety","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2601.06631","title":"Labels have Human Values: Value Calibration of Subjective Tasks","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2602.03709","title":"No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.06552","title":"KCLarity at SemEval-2026 Task 6: Encoder and Zero-Shot Approaches to Political Evasion Detection","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.21404","title":"Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2605.06318","title":"Who and What? Using Linguistic Features and Annotator Characteristics to Analyze Annotation Variation","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2410.15726","title":"Reducing annotator bias by belief elicitation","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2508.06204","title":"Classification is a RAG problem: A case study on hate speech detection","created":"2025-08-08","cited_by_count":0,"area":"rag"},{"id":"2508.11434","title":"Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discourse","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.08217","title":"Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions","created":"2025-09-10","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":"2601.02337","title":"Robust Persona-Aware Toxicity Detection with Prompt Optimization and Learned Ensembling","created":"2026-01-05","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":"2605.05329","title":"Understanding Annotator Safety Policy with Interpretability","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.22373","title":"Boundary-targeted Membership Inference Attacks on Safety Classifiers","created":"2026-05-21","cited_by_count":0,"area":"safety"},{"id":"2605.27313","title":"When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.07629","title":"Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences","created":"2026-05-30","cited_by_count":0,"area":"alignment"},{"id":"2606.28772","title":"Majority Vote Silences Minority Values: Annotator Disagreement at the Hate/Offensive Boundary in HateXplain","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.04890","title":"Evaluating Large Language Models for Antisemitic Incident Classification","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08493","title":"Ensemble Diversity Optimization for Subjective Supervision","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.12330","title":"Reliability-Aware Sexism Detection: Combining DPO with Annotator Agreement and Token-Level Confidence Scoring","created":"2026-06-01","cited_by_count":0,"area":"alignment"},{"id":"2609.00764","title":"Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.24516","title":"LLJ Cards: Best practices for the Use of LLMs as Judges","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.33282","title":"Multi-Dimensional Comparative Scale Construction for Efficient Personalized Subjective Judgment in High-Traffic Applications","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.18588","title":"Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}