{"total":14,"rows":[{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2511.05162","title":"Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results","created":"2025-11-07","cited_by_count":10,"area":null},{"id":"2503.12440","title":"HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2501.02266","title":"LLMzSz{\\L}: a comprehensive LLM benchmark for Polish","created":"2025-01-04","cited_by_count":7,"area":null},{"id":"2507.08924","title":"From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2506.22439","title":"Psycholinguistic Word Features: a New Approach for the Evaluation of LLMs Alignment with Humans","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2509.14405","title":"Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings","created":"2025-09-17","cited_by_count":3,"area":null},{"id":"2408.02239","title":"Pula: Training Large Language Models for Setswana","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2507.00999","title":"La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2507.19699","title":"Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2508.02635","title":"Test Set Quality in Multilingual LLM Evaluation","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2605.24904","title":"Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2508.13526","title":"MATA: Mindful Assessment of the Telugu Abilities of Large Language Models","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2604.01957","title":"Diagnosing Translated Benchmarks: An Automated Quality Assurance Study of the EU20 Benchmark Suite","created":"2026-04-02","cited_by_count":0,"area":null}],"next_cursor":null}