{"total":39,"rows":[{"id":"2410.18889","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","created":"2024-10-24","cited_by_count":20,"area":null},{"id":"2404.15720","title":"Annotator-Centric Active Learning for Subjective NLP Tasks","created":"2024-04-24","cited_by_count":18,"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":"2412.13942","title":"A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI","created":"2024-12-18","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":"2507.18890","title":"NUTMEG: Separating Signal From Noise in Annotator Disagreement","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2406.19803","title":"Scalable and Domain-General Abstractive Proposition Segmentation","created":"2024-06-28","cited_by_count":6,"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":"2510.16458","title":"Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations","created":"2025-10-18","cited_by_count":5,"area":null},{"id":"2505.22848","title":"LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2505.23183","title":"Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2507.02593","title":"Revisiting Active Learning under (Human) Label Variation","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2507.15114","title":"From Disagreement to Understanding: The Case for Ambiguity Detection in NLI","created":"2025-07-20","cited_by_count":4,"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":"2412.11750","title":"Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varieties","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2507.13318","title":"HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals","created":"2025-07-17","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":"2510.12817","title":"From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2508.08163","title":"LPI-RIT at LeWiDi-2025: Improving Distributional Predictions via Metadata and Loss Reweighting with DisCo","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2512.15248","title":"The Moralization Corpus: Frame-Based Annotation and Analysis of Moralizing Speech Acts across Diverse Text Genres","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2604.07591","title":"From Ground Truth to Measurement: A Statistical Framework for Human Labeling","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2510.07105","title":"Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2602.23546","title":"Humans and LLMs Diverge on Probabilistic Inferences","created":"2026-02-26","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":"2605.01168","title":"Quantifying and Predicting Disagreement in Graded Human Ratings","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2607.15870","title":"How Much Human Label Variation Does Formal Semantic Structure Explain? Group-Level Effects and Item-Level Ceilings in NLI","created":"2026-07-17","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":"2509.09524","title":"DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.17794","title":"Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction","created":"2025-09-22","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":"2510.24295","title":"MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.08949","title":"EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2602.22723","title":"Human Label Variation in Implicit Discourse Relation Recognition","created":"2026-02-26","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":"2604.21667","title":"Fine-Grained Perspectives: Modeling Explanations with Annotator-Specific Rationales","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.25383","title":"Introducing corpora Hlava Cor and Hlava AD: Human Label Variation in Coreference and Discourse Relations","created":"2026-06-24","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":"2608.15363","title":"A Multi-Annotator Study of Segmentation Noise and Uncertainty in Turbid Underwater Images","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.24877","title":"Decomposing Error and Style in Automated Clinical Coding","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}