{"total":39,"rows":[{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168,"area":null},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146,"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":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"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":"2404.06644","title":"Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?","created":"2024-04-09","cited_by_count":22,"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":"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":"2404.02403","title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","created":"2024-04-03","cited_by_count":11,"area":null},{"id":"2402.06617","title":"FaBERT: Pre-training BERT on Persian Blogs","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2502.11571","title":"FaMTEB: Massive Text Embedding Benchmark in Persian Language","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2112.07522","title":"LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2502.07459","title":"PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian","created":"2025-02-11","cited_by_count":8,"area":null},{"id":"2401.06466","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","created":"2024-01-12","cited_by_count":7,"area":null},{"id":"2407.16382","title":"TookaBERT: A Step Forward for Persian NLU","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2505.11665","title":"Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2112.13634","title":"A Survey on non-English Question Answering Dataset","created":"2021-12-27","cited_by_count":5,"area":null},{"id":"2303.18162","title":"ViMMRC 2.0 -- Enhancing Machine Reading Comprehension on Vietnamese Literature Text","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2106.03983","title":"Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2505.16000","title":"Leveraging Online Data to Enhance Medical Knowledge in a Small Persian Language Model","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2508.02241","title":"Isolating Culture Neurons in Multilingual Large Language Models","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2304.07127","title":"OPI at SemEval 2023 Task 1: Image-Text Embeddings and Multimodal Information Retrieval for Visual Word Sense Disambiguation","created":"2023-04-14","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":"2109.04098","title":"ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization","created":"2021-09-09","cited_by_count":2,"area":null},{"id":"2407.11186","title":"Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2408.08848","title":"PsychoLex: Unveiling the Psychological Mind of Large Language Models","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2302.00321","title":"An Evaluation of Persian-English Machine Translation Datasets with Transformers","created":"2023-02-01","cited_by_count":1,"area":null},{"id":"2510.12807","title":"Benchmarking Open-Source Large Language Models for Persian in Zero-Shot and Few-Shot Learning","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2602.17623","title":"Unmasking the Factual-Conceptual Gap in Persian Language Models","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.14456","title":"PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2205.08755","title":"Persian Natural Language Inference: A Meta-learning approach","created":"2022-05-18","cited_by_count":0,"area":null},{"id":"2509.21104","title":"PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.15134","title":"FarsiMCQGen: a Persian Multiple-choice Question Generation Framework","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2602.22827","title":"TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2605.27015","title":"PersLitEval: Fine-grained Benchmark and Evaluation of LLMs on Persian Literature Questions","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.20089","title":"IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.24698","title":"The Annotation Bottleneck in Persian Text NLP: Persian as an Annotation-Scarce Language","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.01810","title":"TalkFa: A Unified Benchmark for Farsi Dialogue Generation and Understanding","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}