{"total":38,"rows":[{"id":"2410.08948","title":"Emergent social conventions and collective bias in LLM populations","created":"2024-10-11","cited_by_count":123,"area":null},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2501.09731","title":"Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI","created":"2025-01-16","cited_by_count":34,"area":null},{"id":"2602.15785","title":"This human study did not involve human subjects: Validating LLM simulations as behavioral evidence","created":"2026-02-17","cited_by_count":29,"area":null},{"id":"2506.07949","title":"Cost-Optimal Active AI Model Evaluation","created":"2025-06-09","cited_by_count":19,"area":null},{"id":"2601.20251","title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","created":"2026-01-28","cited_by_count":18,"area":null},{"id":"2507.09108","title":"SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation","created":"2025-07-12","cited_by_count":12,"area":null},{"id":"2503.01513","title":"Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2505.20178","title":"No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2506.10908","title":"Probably Approximately Correct Labels","created":"2025-06-12","cited_by_count":8,"area":null},{"id":"2411.19908","title":"Another look at statistical inference with machine learning-imputed data","created":"2024-11-29","cited_by_count":7,"area":null},{"id":"2605.05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","created":"2026-05-07","cited_by_count":7,"area":null},{"id":"2511.08991","title":"Robust Sampling for Active Statistical Inference","created":"2025-11-12","cited_by_count":6,"area":null},{"id":"2503.17569","title":"Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2604.18569","title":"Revisiting Active Sequential Prediction-Powered Mean Estimation","created":"2026-04-20","cited_by_count":4,"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":"2508.17164","title":"The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum","created":"2025-08-23","cited_by_count":3,"area":null},{"id":"2510.14581","title":"Model-agnostic Selective Labeling with Provable Statistical Guarantees","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2601.15773","title":"Next Generation Active Learning: Mixture of LLMs in the Loop","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2607.05046","title":"CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion","created":"2026-07-06","cited_by_count":3,"area":null},{"id":"2508.04915","title":"ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2510.03541","title":"What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2606.11018","title":"Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2606.27687","title":"Mitigating LLM-based p-Hacking by Preregistering for the Next LLM","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2506.08593","title":"Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2601.11920","title":"Enhancing LLM-Based Data Annotation with Error Decomposition","created":"2026-01-17","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":"2605.09834","title":"Supercharging Bayesian Inference with Reliable AI-Informed Priors","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2502.07186","title":"PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2508.14032","title":"The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2601.09905","title":"Self-reflection in Automated Qualitative Coding: Improving Text Annotation through Secondary LLM Critique","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2602.03791","title":"Should I use Synthetic Data for That? An Analysis of the Suitability of Synthetic Data for Data Sharing and Augmentation","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2605.10713","title":"Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11638","title":"Learning U-Statistics with Active Inference","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.02911","title":"The Ghost Annotator: a Framework to Explore Human Label Variation in Content Moderation through Conformal Prediction","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.05052","title":"Beyond Independent Labels: Schwartz-Geometry Decoding for Human Value Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.27974","title":"QUORUM: QUality-Optimized Routing Using Multiple annotators","created":"2026-08-28","cited_by_count":0,"area":null}],"next_cursor":null}