{"total":53,"rows":[{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2106.08087","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","created":"2021-06-15","cited_by_count":101,"area":null},{"id":"2106.12066","title":"It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning","created":"2021-06-22","cited_by_count":69,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2309.10931","title":"A Family of Pretrained Transformer Language Models for Russian","created":"2023-09-19","cited_by_count":27,"area":null},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2201.02387","title":"The Defeat of the Winograd Schema Challenge","created":"2022-01-07","cited_by_count":25,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2401.04531","title":"MERA: A Comprehensive LLM Evaluation in Russian","created":"2024-01-09","cited_by_count":22,"area":null},{"id":"2408.12503","title":"The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design","created":"2024-08-22","cited_by_count":20,"area":null},{"id":"2304.00906","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","created":"2023-04-03","cited_by_count":16,"area":null},{"id":"2208.04826","title":"Compositional Evaluation on Japanese Textual Entailment and Similarity","created":"2022-08-09","cited_by_count":14,"area":null},{"id":"2211.13112","title":"This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2405.13929","title":"Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2210.12813","title":"TAPE: Assessing Few-shot Russian Language Understanding","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2201.06499","title":"RuMedBench: A Russian Medical Language Understanding Benchmark","created":"2022-01-17","cited_by_count":10,"area":null},{"id":"2406.04215","title":"mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans","created":"2024-06-06","cited_by_count":10,"area":"lr"},{"id":"2202.04994","title":"Slovene SuperGLUE Benchmark: Translation and Evaluation","created":"2022-02-10","cited_by_count":7,"area":null},{"id":"2205.02340","title":"Knowledge Distillation of Russian Language Models with Reduction of Vocabulary","created":"2022-05-04","cited_by_count":7,"area":"distill"},{"id":"2304.01922","title":"Resources and Few-shot Learners for In-context Learning in Slavic Languages","created":"2023-04-04","cited_by_count":6,"area":null},{"id":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2108.12626","title":"HeadlineCause: A Dataset of News Headlines for Detecting Causalities","created":"2021-08-28","cited_by_count":5,"area":null},{"id":"2305.06545","title":"GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2308.09435","title":"A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages","created":"2023-08-18","cited_by_count":5,"area":null},{"id":"2312.02598","title":"Impact of Tokenization on LLaMa Russian Adaptation","created":"2023-12-05","cited_by_count":5,"area":null},{"id":"2404.05333","title":"PORTULAN ExtraGLUE Datasets and Models: Kick-starting a Benchmark for the Neural Processing of Portuguese","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2403.17553","title":"RuBia: A Russian Language Bias Detection Dataset","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2112.02325","title":"A Russian Jeopardy! Data Set for Question-Answering Systems","created":"2021-12-04","cited_by_count":3,"area":null},{"id":"2503.13102","title":"REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2506.21508","title":"skLEP: A Slovak General Language Understanding Benchmark","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2202.07791","title":"Russian SuperGLUE 1.1: Revising the Lessons not Learned by Russian NLP models","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2205.10687","title":"Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding","created":"2022-05-21","cited_by_count":2,"area":null},{"id":"2105.01192","title":"Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks","created":"2021-05-03","cited_by_count":1,"area":null},{"id":"2108.02605","title":"EENLP: Cross-lingual Eastern European NLP Index","created":"2021-08-05","cited_by_count":1,"area":null},{"id":"2212.10461","title":"Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2402.14890","title":"Vygotsky Distance: Measure for Benchmark Task Similarity","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2405.18375","title":"Thai Winograd Schemas: A Benchmark for Thai Commonsense Reasoning","created":"2024-05-28","cited_by_count":1,"area":"lr"},{"id":"2408.02439","title":"Long Input Benchmark for Russian Analysis","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2410.13666","title":"VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2509.23529","title":"DOoM: Difficult Olympiads of Math","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2511.15552","title":"Multimodal Evaluation of Russian-language Architectures","created":"2025-11-19","cited_by_count":1,"area":"mllm"},{"id":"2104.14314","title":"MOROCCO: Model Resource Comparison Framework","created":"2021-04-29","cited_by_count":0,"area":null},{"id":"2106.10487","title":"Transformers for Headline Selection for Russian News Clusters","created":"2021-06-19","cited_by_count":0,"area":null},{"id":"2201.03521","title":"Polish Natural Language Inference and Factivity -- an Expert-based Dataset and Benchmarks","created":"2022-01-10","cited_by_count":0,"area":null},{"id":"2306.04523","title":"Can current NLI systems handle German word order? Investigating language model performance on a new German challenge set of minimal pairs","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2505.24616","title":"Eye of Judgement: Dissecting the Evaluation of Russian-speaking LLMs with POLLUX","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2511.17290","title":"Estonian WinoGrande Dataset: Comparative Analysis of LLM Performance on Human and Machine Translation","created":"2025-11-21","cited_by_count":0,"area":"lr"},{"id":"2604.03672","title":"AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.17976","title":"ltzGLUE: Luxembourgish General Language Understanding Evaluation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.29807","title":"Data filtering methods for training language models","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}