{"total":24,"rows":[{"id":"2402.13211","title":"Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation","created":"2024-02-20","cited_by_count":55,"area":null},{"id":"2405.05894","title":"Efficient LLM Comparative Assessment: a Product of Experts Framework for Pairwise Comparisons","created":"2024-05-09","cited_by_count":22,"area":null},{"id":"2412.18407","title":"A Statistical Framework for Ranking LLM-Based Chatbots","created":"2024-12-24","cited_by_count":12,"area":null},{"id":"2409.11904","title":"Finding the Subjective Truth: Collecting 2 Million Votes for Comprehensive Gen-AI Model Evaluation","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2410.08917","title":"AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2310.00260","title":"On Sinkhorn's Algorithm and Choice Modeling","created":"2023-09-30","cited_by_count":6,"area":null},{"id":"2312.04711","title":"Luck, skill, and depth of competition in games and social hierarchies","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2406.16507","title":"Statistical ranking with dynamic covariates","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2505.15240","title":"Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2507.01633","title":"Confidence and Stability of Global and Pairwise Scores in NLP Evaluation","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2401.08463","title":"Statistical inference for pairwise comparison models","created":"2024-01-16","cited_by_count":3,"area":null},{"id":"2412.11314","title":"Reliable, Reproducible, and Really Fast Leaderboards with Evalica","created":"2024-12-15","cited_by_count":3,"area":null},{"id":"2501.02505","title":"Estimation of partial rankings from sparse, noisy comparisons","created":"2025-01-05","cited_by_count":3,"area":null},{"id":"2508.19780","title":"Interestingness First Classifiers","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2607.22221","title":"Convergence analysis of a family of Zermelo-type iterations for the Bradley--Terry model","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2409.04479","title":"Absolute Ranking: An Essential Normalization for Benchmarking Optimization Algorithms","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2410.17604","title":"Ranking of Multi-Response Experiment Treatments","created":"2024-10-23","cited_by_count":0,"area":null},{"id":"2504.16093","title":"Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Model","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2510.22219","title":"Estimating the Error of Large Language Models at Pairwise Text Comparison","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2601.23128","title":"Distribution-informed Efficient Conformal Prediction for Full Ranking","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.00641","title":"On rankings in multiplayer games with an application to the game of Whist","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.03840","title":"New insights into Elo algorithm for practitioners and statisticians","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.30447","title":"Calibrated Preference Learning: The Case of Label Ranking","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.20565","title":"Steering the Compass: Aligning Dynamic Psychological Counseling Conversations with Cognitive Behavioral Therapy Strategies","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}