{"total":35,"rows":[{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"area":null},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35,"area":null},{"id":"2110.10746","title":"Better than Average: Paired Evaluation of NLP Systems","created":"2021-10-20","cited_by_count":30,"area":null},{"id":"2106.00794","title":"What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks?","created":"2021-06-01","cited_by_count":23,"area":null},{"id":"2501.18251","title":"How to Select Datapoints for Efficient Human Evaluation of NLG Models?","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2203.01282","title":"py-irt: A Scalable Item Response Theory Library for Python","created":"2022-03-02","cited_by_count":19,"area":null},{"id":"2407.15645","title":"Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2406.14230","title":"Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2506.09796","title":"Do LLMs Give Psychometrically Plausible Responses in Educational Assessments?","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2106.06849","title":"Can Transformer Language Models Predict Psychometric Properties?","created":"2021-06-12","cited_by_count":8,"area":null},{"id":"2406.16342","title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2408.05326","title":"A Psychology-based Unified Dynamic Framework for Curriculum Learning","created":"2024-08-09","cited_by_count":6,"area":null},{"id":"2602.07267","title":"BRIDGE: Predicting Human Task Completion Time From Model Performance","created":"2026-02-06","cited_by_count":6,"area":null},{"id":"2404.07720","title":"Automatic Generation and Evaluation of Reading Comprehension Test Items with Large Language Models","created":"2024-04-11","cited_by_count":5,"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":"2210.04317","title":"A Spectral Approach to Item Response Theory","created":"2022-10-09","cited_by_count":4,"area":null},{"id":"2509.22888","title":"JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2510.25064","title":"Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2607.15190","title":"Can We Trust Item Response Theory for AI Evaluation?","created":"2026-07-16","cited_by_count":4,"area":null},{"id":"2503.05888","title":"QG-SMS: Enhancing Test Item Analysis via Student Modeling and Simulation","created":"2025-03-07","cited_by_count":3,"area":null},{"id":"2304.06337","title":"Computational modeling of semantic change","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2401.11185","title":"How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation","created":"2024-01-20","cited_by_count":1,"area":null},{"id":"2404.01799","title":"PATCH! {P}sychometrics-{A}ssis{T}ed Ben{CH}marking of Large Language Models against Human Populations: A Case Study of Proficiency in 8th Grade Mathematics","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2604.21766","title":"AUDITA: A New Dataset to Audit Humans vs. AI Skill at Audio QA","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.26429","title":"DualEval: Joint Model-Item Calibration for Unified LLM Evaluation","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.02586","title":"Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.05086","title":"Item Response Theory for AI Safety","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.22295","title":"LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model","created":"2026-08-23","cited_by_count":1,"area":null},{"id":"2307.07134","title":"Multi-Dimensional Ability Diagnosis for Machine Learning Algorithms","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2601.17399","title":"ReLE: A Scalable System and Structured Benchmark for Diagnosing Capability Anisotropy in Chinese LLMs","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2605.16290","title":"MCQ Difficulty Prediction via Modeling Learner Heterogeneity Using Data-Driven Cognitive Profiling","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.19066","title":"The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.20626","title":"Efficient Safety Benchmarking via Item Response Theory","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2609.35646","title":"Rubric Rewards from Item Response Theory","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}