{"total":28,"rows":[{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103,"area":null},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2504.15521","title":"The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks","created":"2025-04-22","cited_by_count":31,"area":null},{"id":"2410.05873","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2505.21693","title":"MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs","created":"2025-05-27","cited_by_count":13,"area":null},{"id":"2412.17933","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2501.00593","title":"Setting Standards in Turkish NLP: TR-MMLU for Large Language Model Evaluation","created":"2024-12-31","cited_by_count":11,"area":null},{"id":"2502.11020","title":"TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2508.16431","title":"Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish","created":"2025-08-22","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":"2601.11778","title":"Translation as a Scalable Proxy for Multilingual Evaluation","created":"2026-01-16","cited_by_count":6,"area":null},{"id":"2602.05150","title":"GreekMMLU: A Native-Sourced Multitask Benchmark for Evaluating Language Models in Greek","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2601.07020","title":"TurkBench: A Benchmark for Evaluating Turkish Large Language Models","created":"2026-01-11","cited_by_count":5,"area":null},{"id":"2505.16591","title":"Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2608.25089","title":"Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation","created":"2026-08-25","cited_by_count":3,"area":null},{"id":"2503.11911","title":"LAG-MMLU: Benchmarking Frontier LLM Understanding in Latvian and Giriama","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2508.13044","title":"B\\\"{u}y\\\"{u}k Dil Modelleri i\\c{c}in TR-MMLU Benchmark{\\i}: Performans De\\u{g}erlendirmesi, Zorluklar ve \\.{I}yile\\c{s}tirme F{\\i}rsatlar{\\i}","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2510.21193","title":"Estonian Native Large Language Model Benchmark","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2609.25081","title":"ufakzeka-1: Building and Evaluating a 151M-Parameter Turkish Language Model from Scratch","created":"2026-09-18","cited_by_count":2,"area":null},{"id":"2502.12895","title":"Multilingual European Language Models: Benchmarking Approaches and Challenges","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2602.19174","title":"TurkicNLP: An NLP Toolkit for Turkic Languages","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2610.02293","title":"HakemBench: A Turkish Benchmark of Typed Decisions","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2411.12921","title":"A Comparative Study of Text Retrieval Models on DaReCzech","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2603.09996","title":"There Are No Silly Questions: Evaluation of Offline LLM Capabilities from a Turkish Perspective","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","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":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.28007","title":"Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}