{"total":26,"rows":[{"id":"2403.12025","title":"A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models","created":"2024-03-18","cited_by_count":45,"area":null},{"id":"2405.18027","title":"TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2210.05725","title":"Measuring and Improving Semantic Diversity of Dialogue Generation","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2402.14146","title":"Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation","created":"2024-02-21","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":"2404.10857","title":"D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation","created":"2024-04-16","cited_by_count":11,"area":null},{"id":"2408.08411","title":"Rater Cohesion and Quality from a Vicarious Perspective","created":"2024-08-15","cited_by_count":8,"area":null},{"id":"2203.12913","title":"k-Rater Reliability: The Correct Unit of Reliability for Aggregated Human Annotations","created":"2022-03-24","cited_by_count":7,"area":null},{"id":"2509.22367","title":"What Is The Political Content in LLMs' Pre- and Post-Training Data?","created":"2025-09-26","cited_by_count":7,"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":"2308.12885","title":"Collect, Measure, Repeat: Reliability Factors for Responsible AI Data Collection","created":"2023-08-22","cited_by_count":5,"area":null},{"id":"2311.09661","title":"Evolving Domain Adaptation of Pretrained Language Models for Text Classification","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2211.13709","title":"Undesirable Biases in NLP: Addressing Challenges of Measurement","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2407.11930","title":"Localizing and Mitigating Errors in Long-form Question Answering","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2409.09135","title":"Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2601.04350","title":"RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2303.04526","title":"Student's t-Distribution: On Measuring the Inter-Rater Reliability When the Observations are Scarce","created":"2023-03-08","cited_by_count":2,"area":null},{"id":"2510.18582","title":"Beyond the Explicit: A Bilingual Dataset for Dehumanization Detection in Social Media","created":"2025-10-21","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":"2512.09662","title":"Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2608.10810","title":"Surfacing the Unsaid: CUE-Bench for Affective Stance in Chinese Discourse","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2511.21912","title":"Tracing How Annotators Think: Augmenting Preference Judgments with Reading Processes","created":"2025-11-26","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":"2605.03147","title":"Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2608.01724","title":"TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.03953","title":"Beyond Majority Vote: Multi-Perspective Adjudication for Medical Hallucination Detection","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}