{"total":50,"rows":[{"id":"2405.01299","title":"The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation","created":"2024-05-02","cited_by_count":29,"area":null},{"id":"2406.17600","title":"\"Seeing the Big through the Small\": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?","created":"2024-06-25","cited_by_count":17,"area":null},{"id":"2502.06207","title":"Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2404.08359","title":"Improving Health Question Answering with Reliable and Time-Aware Evidence Retrieval","created":"2024-04-12","cited_by_count":12,"area":null},{"id":"2402.07767","title":"Text Detoxification as Style Transfer in English and Hindi","created":"2024-02-12","cited_by_count":11,"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":"2402.02844","title":"Comparing Knowledge Sources for Open-Domain Scientific Claim Verification","created":"2024-02-05","cited_by_count":10,"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":"2510.08460","title":"LeWiDi-2025 at NLPerspectives: Third Edition of the Learning with Disagreements Shared Task","created":"2025-10-09","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":"2502.01891","title":"Training and Evaluating with Human Label Variation: An Empirical Study","created":"2025-02-03","cited_by_count":8,"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":"2311.03153","title":"Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It's Best to Relate Perspectives!","created":"2023-11-06","cited_by_count":5,"area":null},{"id":"2402.01423","title":"Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2502.14501","title":"Towards a Perspectivist Turn in Argument Quality Assessment","created":"2025-02-20","cited_by_count":5,"area":null},{"id":"2511.14662","title":"Bias in, Bias out: Annotation Bias in Multilingual Large Language Models","created":"2025-11-18","cited_by_count":5,"area":null},{"id":"2411.10080","title":"Understanding The Effect Of Temperature On Alignment With Human Opinions","created":"2024-11-15","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":"2312.07228","title":"Toxic language detection: a systematic review of Arabic datasets","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2503.00489","title":"Embracing Diversity: A Multi-Perspective Approach with Soft Labels","created":"2025-03-01","cited_by_count":3,"area":null},{"id":"2508.17164","title":"The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum","created":"2025-08-23","cited_by_count":3,"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":"2408.02257","title":"To Aggregate or Not to Aggregate. That is the Question: A Case Study on Annotation Subjectivity in Span Prediction","created":"2024-08-05","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":"2605.10415","title":"Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2305.01050","title":"SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation","created":"2023-05-01","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":"2510.17548","title":"When Annotators Disagree, Topology Explains: Mapper, a Topological Tool for Exploring Text Embedding Geometry and Ambiguity","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2602.18693","title":"Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2604.18069","title":"Modeling Human Perspectives with Socio-Demographic Representations","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.21069","title":"Quality and Agreement in Multilabel Emotion Annotation: A Case Study and Evaluation Framework","created":"2026-06-19","cited_by_count":1,"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":"2510.12036","title":"On the Interplay between Human Label Variation and Model Fairness","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.13259","title":"Hypernetworks for Perspectivist Adaptation","created":"2025-10-15","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":"2604.16332","title":"Annotation Entropy Predicts Per-Example Learning Dynamics in LoRA Fine-Tuning","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.21667","title":"Fine-Grained Perspectives: Modeling Explanations with Annotator-Specific Rationales","created":"2026-04-23","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":"2605.09955","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":"2605.11398","title":"AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.20642","title":"Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions","created":"2026-05-20","cited_by_count":0,"area":null},{"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":"2607.08493","title":"Ensemble Diversity Optimization for Subjective Supervision","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.15619","title":"Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.22432","title":"Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering Calibrator","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.06646","title":"When Does a Laugh Begin? Structured Annotator Disagreement in Temporal Laughter Localization","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.24028","title":"When Evidence Conflicts: Reliability-aware Meta-review Generation","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}