{"total":34,"rows":[{"id":"2406.03181","title":"Missci: Reconstructing Fallacies in Misrepresented Science","created":"2024-06-05","cited_by_count":14,"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":"2409.19505","title":"The Nature of NLP: Analyzing Contributions in NLP Papers","created":"2024-09-29","cited_by_count":12,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2405.11919","title":"On Efficient and Statistical Quality Estimation for Data Annotation","created":"2024-05-20","cited_by_count":8,"area":null},{"id":"2502.07732","title":"When Incentives Backfire, Data Stops Being Human","created":"2025-02-11","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":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2411.04637","title":"Hands-On Tutorial: Labeling with LLM and Human-in-the-Loop","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2504.19472","title":"Conflicts in Texts: Data, Implications and Challenges","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2505.15087","title":"HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.20826","title":"AdParaphrase v2.0: Generating Attractive Ad Texts Using a Preference-Annotated Paraphrase Dataset","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2505.24571","title":"Identifying Primary Stress Across Related Languages and Dialects with Transformer-based Speech Encoder Models","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2506.20876","title":"Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2510.06250","title":"Scalable multilingual PII annotation for responsible AI in LLMs","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2510.23536","title":"IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering","created":"2025-10-27","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":"2608.15242","title":"LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2508.20468","title":"ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.17449","title":"SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2511.07286","title":"Glioma C6: A Novel Dataset for Training and Benchmarking Cell Segmentation","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2606.02255","title":"Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025","created":"2026-06-01","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":"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":"2601.01350","title":"FC-CONAN: An Exhaustively Paired Dataset for Robust Evaluation of Retrieval Systems","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2601.16800","title":"Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2603.00114","title":"Automated Quality Check of Sensor Data Annotations","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2605.03624","title":"Annotation Quality in Aspect-Based Sentiment Analysis: A Case Study Comparing Experts, Students, Crowdworkers, and Large Language Model","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.04886","title":"BenCSSmark: Making the Social Sciences Count in LLM Research","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.26070","title":"WhoSaidIt: Human-LLM Collaborative Annotation for Text-Based Multilingual Speaker-Attribute Classification","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.27239","title":"Temporal Simultaneity Predicts Annotation Quality in Sentiment Corpora","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.14942","title":"Looks Can be Deceiving: Annotator and Reviewer Performance Across Imagery Sources in Crowd-Sourced Aerial Damage Assessment","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.24516","title":"LLJ Cards: Best practices for the Use of LLMs as Judges","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.10805","title":"Whose Ground Truth? Embracing Ambiguity in Human-Centered AI","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}