{"total":33,"rows":[{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2501.12557","title":"Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review","created":"2025-01-22","cited_by_count":16,"area":null},{"id":"2502.11267","title":"Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent","created":"2025-02-16","cited_by_count":15,"area":null},{"id":"2407.04693","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","created":"2024-07-05","cited_by_count":14,"area":null},{"id":"2405.16402","title":"Assessing Empathy in Large Language Models with Real-World Physician-Patient Interactions","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2408.10902","title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs","created":"2024-08-20","cited_by_count":10,"area":null},{"id":"2403.20262","title":"ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models","created":"2024-03-29","cited_by_count":9,"area":null},{"id":"2409.12218","title":"ARTICLE: Annotator Reliability Through In-Context Learning","created":"2024-09-18","cited_by_count":6,"area":null},{"id":"2408.01527","title":"Using LLMs to Establish Implicit User Sentiment of Software Desirability","created":"2024-08-02","cited_by_count":4,"area":null},{"id":"2410.17099","title":"Human-LLM Hybrid Text Answer Aggregation for Crowd Annotations","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2409.00940","title":"Large Language Models for Automatic Detection of Sensitive Topics","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2409.10702","title":"Model-in-the-Loop (MILO): Accelerating Multimodal AI Data Annotation with LLMs","created":"2024-09-16","cited_by_count":3,"area":null},{"id":"2507.00828","title":"ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering","created":"2025-07-01","cited_by_count":3,"area":null},{"id":"2507.05010","title":"Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2403.05640","title":"Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification","created":"2024-03-08","cited_by_count":2,"area":null},{"id":"2405.05758","title":"Exploring the Human-LLM Synergy in Advancing Theory-driven Qualitative Analysis","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2512.19903","title":"How well do Large Language Models Recognize Instructional Moves? Establishing Baselines for Foundation Models in Educational Discourse","created":"2025-12-22","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":"2408.06494","title":"What Color Scheme is More Effective in Assisting Readers to Locate Information in a Color-Coded Article?","created":"2024-08-12","cited_by_count":1,"area":null},{"id":"2412.11978","title":"Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2503.11096","title":"Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2512.15979","title":"OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2602.04574","title":"Probabilistic Label Spreading: Efficient and Consistent Estimation of Soft Labels with Epistemic Uncertainty on Graphs","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.25269","title":"When Hate Meets Facts: LLMs-in-the-Loop for Check-worthiness Detection in Hate Speech","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2608.29455","title":"Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2503.21000","title":"Improving User Behavior Prediction: Leveraging Annotator Metadata in Supervised Machine Learning Models","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2601.03435","title":"The Critical Role of Aspects in Measuring Document Similarity","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","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":"2606.23701","title":"Evaluating LLM Usage for Efficient and Explainable Numerical and Classified Implicit Sentiment Analysis of Product Desirability","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2609.26926","title":"Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.38799","title":"Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}