{"total":16,"rows":[{"id":"2406.19356","title":"DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions","created":"2024-06-27","cited_by_count":7,"area":null},{"id":"2603.27187","title":"Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention","created":"2026-03-28","cited_by_count":6,"area":null},{"id":"2502.16358","title":"Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores","created":"2025-02-22","cited_by_count":5,"area":null},{"id":"2508.11184","title":"Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2511.06530","title":"Better Datasets Start From RefineLab: Automatic Optimization for High-Quality Dataset Refinement","created":"2025-11-09","cited_by_count":3,"area":null},{"id":"2507.04793","title":"A Survey of Pun Generation: Datasets, Evaluations and Methodologies","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2605.12398","title":"Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2504.13439","title":"D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Model","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2506.00612","title":"Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2505.02850","title":"Harnessing Structured Knowledge: A Concept Map-Based Approach for High-Quality Multiple Choice Question Generation with Effective Distractors","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2506.15598","title":"From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns","created":"2025-06-18","cited_by_count":0,"area":null},{"id":"2602.17377","title":"Corpus Prevalence of Multiple-Choice Question Options","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.16241","title":"BAGEL: Benchmarking Animal Knowledge Expertise in Language Models","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2609.04384","title":"You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.15467","title":"Turkish MMLU Pro: Traceable Option Augmentation and Its Validity Limits in Turkish Multiple-Choice Evaluation","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.26087","title":"The Architect, the Adversary, and the Judge: Closed-Loop Generation of Standards-Aligned Assessment Items at Scale","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}