{"total":20,"rows":[{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2503.14996","title":"Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering","created":"2025-03-19","cited_by_count":28,"area":null},{"id":"2503.01622","title":"DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"id":"2503.16167","title":"CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2502.18798","title":"Choices Speak Louder than Questions","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2606.11643","title":"Improving Cross-Format Robustness in Language Models with Multi-Format Training","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2609.39496","title":"When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev","created":"2026-09-30","cited_by_count":2,"area":null},{"id":"2412.04277","title":"Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2506.11007","title":"Impact of Comments on LLM Comprehension of Legacy Code","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2511.21860","title":"Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2512.23711","title":"CAT: A Metric-Driven Framework for Analyzing the Consistency-Accuracy Relation of LLMs under Controlled Input Variations","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2604.06210","title":"Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook","created":"2026-03-16","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":"2607.00664","title":"YOMI-Bench: A Benchmark for Evaluating Kanji Reading and Phonological Understanding of LLMs for Japanese","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.11947","title":"A, B, C, or Stable? Accuracy and Order Sensitivity Diverge in LLM Multiple-Choice Evaluation","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2601.13300","title":"OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2605.06382","title":"Rethinking Vacuity for OOD Detection in Evidential Deep Learning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2609.07309","title":"LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error and Robustness Nuances","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.16713","title":"Audit Before You Distill: A Controlled Workflow for Reasoning Transfer into Compact Medical Language Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}