{"total":17,"rows":[{"id":"2411.02414","title":"Fairness Evaluation with Item Response Theory","created":"2024-10-20","cited_by_count":7,"area":null},{"id":"2403.00680","title":"Scalable Learning of Item Response Theory Models","created":"2024-03-01","cited_by_count":6,"area":null},{"id":"2601.13885","title":"Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores","created":"2026-01-20","cited_by_count":5,"area":null},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2106.06243","title":"Unsupervised Anomaly Detection Ensembles using Item Response Theory","created":"2021-06-11","cited_by_count":2,"area":null},{"id":"2303.17731","title":"$\\beta^{4}$-IRT: A New $\\beta^{3}$-IRT with Enhanced Discrimination Estimation","created":"2023-03-30","cited_by_count":2,"area":null},{"id":"2307.15850","title":"Comprehensive Algorithm Portfolio Evaluation using Item Response Theory","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.07616","title":"Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2608.02966","title":"Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple-Choice Benchmarks","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2104.02578","title":"Neurons learn slower than they think","created":"2021-04-02","cited_by_count":0,"area":null},{"id":"2109.09500","title":"Deep Learning-Based Estimation and Goodness-of-Fit for Large-Scale Confirmatory Item Factor Analysis","created":"2021-09-20","cited_by_count":0,"area":null},{"id":"2409.04041","title":"On Evaluation of Vision Datasets and Models using Human Competency Frameworks","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2504.02643","title":"A Dynamic, Ordinal Gaussian Process Item Response Theoretic Model","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2507.08487","title":"Enhancing Essay Cohesion Assessment: A Novel Item Response Theory Approach","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2606.07422","title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.27023","title":"BayesAME: Bayesian Active Model Evaluation","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}