{"total":118,"rows":[{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773,"area":null},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437,"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":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218,"area":null},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"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":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126,"area":null},{"id":"2406.07814","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","created":"2024-06-12","cited_by_count":123,"area":"alignment"},{"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":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97,"area":null},{"id":"2305.06626","title":"When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks","created":"2023-05-11","cited_by_count":90,"area":null},{"id":"2310.00907","title":"The Participatory Turn in AI Design: Theoretical Foundations and the Current State of Practice","created":"2023-10-02","cited_by_count":87,"area":null},{"id":"2309.16349","title":"Human Feedback is not Gold Standard","created":"2023-09-28","cited_by_count":83,"area":"alignment"},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2301.05036","title":"Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information","created":"2023-01-12","cited_by_count":52,"area":null},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"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":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2207.00810","title":"Eliciting and Learning with Soft Labels from Every Annotator","created":"2022-07-02","cited_by_count":43,"area":null},{"id":"2305.14663","title":"You Are What You Annotate: Towards Better Models through Annotator Representations","created":"2023-05-24","cited_by_count":40,"area":null},{"id":"2603.03303","title":"HumanLM: Simulating Users with State Alignment Beats Response Imitation","created":"2026-02-07","cited_by_count":37,"area":null},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2205.05057","title":"Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory","created":"2022-05-10","cited_by_count":32,"area":null},{"id":"2210.03709","title":"Understanding Practices, Challenges, and Opportunities for User-Engaged Algorithm Auditing in Industry Practice","created":"2022-10-07","cited_by_count":32,"area":null},{"id":"2307.09302","title":"Conformal prediction under ambiguous ground truth","created":"2023-07-18","cited_by_count":31,"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":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","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":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2506.08119","title":"SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents","created":"2025-06-09","cited_by_count":23,"area":"agents"},{"id":"2407.14916","title":"Improving Context-Aware Preference Modeling for Language Models","created":"2024-07-20","cited_by_count":22,"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":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2409.17213","title":"Plurals: A System for Guiding LLMs Via Simulated Social Ensembles","created":"2024-09-25","cited_by_count":17,"area":null},{"id":"2205.12495","title":"ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection","created":"2022-05-25","cited_by_count":15,"area":"lr"},{"id":"2303.02884","title":"Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design","created":"2023-03-06","cited_by_count":15,"area":null},{"id":"2304.06701","title":"Learning Personalized Decision Support Policies","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2401.07058","title":"Does More Advice Help? The Effects of Second Opinions in AI-Assisted Decision Making","created":"2024-01-13","cited_by_count":14,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2506.11343","title":"From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review","created":"2025-06-12","cited_by_count":11,"area":null},{"id":"2507.13383","title":"Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models","created":"2025-07-15","cited_by_count":11,"area":"alignment"},{"id":"2302.07372","title":"Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection","created":"2023-02-14","cited_by_count":10,"area":null},{"id":"2305.06074","title":"iLab at SemEval-2023 Task 11 Le-Wi-Di: Modelling Disagreement or Modelling Perspectives?","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8,"area":"alignment"},{"id":"2411.05854","title":"Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators","created":"2024-11-06","cited_by_count":8,"area":"safety"},{"id":"2205.06905","title":"Perspectives on Incorporating Expert Feedback into Model Updates","created":"2022-05-13","cited_by_count":7,"area":null},{"id":"2210.15870","title":"\"It's Not Just Hate'': A Multi-Dimensional Perspective on Detecting Harmful Speech Online","created":"2022-10-28","cited_by_count":7,"area":null},{"id":"2307.02191","title":"Evaluating AI systems under uncertain ground truth: a case study in dermatology","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2307.10189","title":"Subjective Crowd Disagreements for Subjective Data: Uncovering Meaningful CrowdOpinion with Population-level Learning","created":"2023-07-07","cited_by_count":7,"area":null},{"id":"2310.02457","title":"The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising \"Alignment\" in Large Language Models","created":"2023-10-03","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":"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":"2210.07934","title":"Codes, Patterns and Shapes of Contemporary Online Antisemitism and Conspiracy Narratives -- an Annotation Guide and Labeled German-Language Dataset in the Context of COVID-19","created":"2022-10-13","cited_by_count":6,"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":"2407.18941","title":"LEMoN: Label Error Detection using Multimodal Neighbors","created":"2024-07-10","cited_by_count":6,"area":"mllm"},{"id":"2207.01059","title":"Identifying the Context Shift between Test Benchmarks and Production Data","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2212.10154","title":"Human-Guided Fair Classification for Natural Language Processing","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2406.12800","title":"Supporting Human Raters with the Detection of Harmful Content using Large Language Models","created":"2024-06-18","cited_by_count":5,"area":"safety"},{"id":"2409.06729","title":"How will advanced AI systems impact democracy?","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2503.12613","title":"Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"id":"2211.13196","title":"SeedBERT: Recovering Annotator Rating Distributions from an Aggregated Label","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2311.03567","title":"Inclusive Portraits: Race-Aware Human-in-the-Loop Technology","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2406.16807","title":"Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation","created":"2024-06-24","cited_by_count":3,"area":"alignment"},{"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":"2501.17899","title":"The Right to AI","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2504.01349","title":"Tasks and Roles in Legal AI: Data Curation, Annotation, and Verification","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2504.03029","title":"Ontologies in Design: How Imagining a Tree Reveals Possibilites and Assumptions in Large Language Models","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2504.04243","title":"Perils of Label Indeterminacy: A Case Study on Prediction of Neurological Recovery After Cardiac Arrest","created":"2025-04-05","cited_by_count":3,"area":null},{"id":"2302.02064","title":"Lived Experience Matters: Automatic Detection of Stigma on Social Media Toward People Who Use Substances","created":"2023-02-04","cited_by_count":2,"area":null},{"id":"2305.15070","title":"Annotation Imputation to Individualize Predictions: Initial Studies on Distribution Dynamics and Model Predictions","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2307.10749","title":"Mitigating Voter Attribute Bias for Fair Opinion Aggregation","created":"2023-07-20","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":"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":"2601.18061","title":"Expert Evaluation and the Limits of Human Feedback in Mental Health AI Safety Testing","created":"2026-01-26","cited_by_count":2,"area":"alignment"},{"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":"2604.21769","title":"Who Defines \"Best\"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2210.12324","title":"Trustworthy Human Computation: A Survey","created":"2022-10-22","cited_by_count":1,"area":null},{"id":"2407.09861","title":"A Systematic Survey of Natural Language Processing for the Greek Language","created":"2024-07-13","cited_by_count":1,"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":"2411.10534","title":"Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment","created":"2024-11-15","cited_by_count":1,"area":"alignment"},{"id":"2412.04025","title":"Exploring the Influence of Label Aggregation on Minority Voices: Implications for Dataset Bias and Model Training","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2509.19643","title":"Human-AI Narrative Synthesis to Foster Shared Understanding in Civic Decision-Making","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2602.22758","title":"Decomposing Physician Disagreement in HealthBench","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.22879","title":"Confidence Calibration under Ambiguous Ground Truth","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.03238","title":"RLHF May Not Reflect Genuine Preferences","created":"2026-01-31","cited_by_count":1,"area":"alignment"},{"id":"2604.17289","title":"REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2605.01168","title":"Quantifying and Predicting Disagreement in Graded Human Ratings","created":"2026-05-01","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":"2309.02912","title":"On the Challenges of Building Datasets for Hate Speech Detection","created":"2023-09-06","cited_by_count":0,"area":null},{"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":"2505.24199","title":"Intuitionistic Fuzzy Sets for Large Language Model Data Annotation: A Novel Approach to Side-by-Side Preference Labeling","created":"2025-05-30","cited_by_count":0,"area":"alignment"},{"id":"2507.12041","title":"Granular feedback merits sophisticated aggregation","created":"2025-07-16","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}