{"total":17,"rows":[{"id":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","cited_by_count":36,"area":null},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"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":"2506.00549","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","created":"2025-05-31","cited_by_count":11,"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":"2308.12885","title":"Collect, Measure, Repeat: Reliability Factors for Responsible AI Data Collection","created":"2023-08-22","cited_by_count":5,"area":null},{"id":"2506.00644","title":"Clinical Annotations for Automatic Stuttering Severity Assessment","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2505.17265","title":"CaseReportBench: An LLM Benchmark Dataset for Dense Information Extraction in Clinical Case Reports","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2302.04562","title":"NLP-based Decision Support System for Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2408.15895","title":"Bias in LLMs as Annotators: The Effect of Party Cues on Labelling Decision by Large Language Models","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2505.22084","title":"MObyGaze: a film dataset of multimodal objectification densely annotated by experts","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2601.08690","title":"All Required, In Order: Phase-Level Evaluation for AI-Human Dialogue in Healthcare and Beyond","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2404.04564","title":"Enhancing Video Summarization with Context Awareness","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2404.09703","title":"AI Competitions and Benchmarks: Dataset Development","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2507.21536","title":"Construction and educational application of a linguistically grounded dependency treebank for Uyghur","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2608.03529","title":"Consensus Measures for Unstructured Biomedical Text Annotations","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2610.19912","title":"Quantifying Annotation Agreement in Object Detection with Optimal Transport","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}