{"total":41,"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":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2109.12068","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","created":"2021-08-31","cited_by_count":63,"area":null},{"id":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47,"area":null},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46,"area":null},{"id":"2502.10361","title":"Enhancing Multilingual LLM Pretraining with Model-Based Data Selection","created":"2025-02-14","cited_by_count":35,"area":null},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2105.01279","title":"ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders","created":"2021-05-04","cited_by_count":22,"area":null},{"id":"2305.14989","title":"Dolphin: A Challenging and Diverse Benchmark for Arabic NLG","created":"2023-05-24","cited_by_count":22,"area":null},{"id":"2403.17848","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","created":"2024-03-26","cited_by_count":20,"area":null},{"id":"2305.14982","title":"LAraBench: Benchmarking Arabic AI with Large Language Models","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2503.14603","title":"Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2505.18152","title":"Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2202.06219","title":"PQuAD: A Persian Question Answering Dataset","created":"2022-02-13","cited_by_count":14,"area":null},{"id":"2109.11314","title":"ParaShoot: A Hebrew Question Answering Dataset","created":"2021-09-23","cited_by_count":12,"area":null},{"id":"2510.13430","title":"Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps","created":"2025-10-15","cited_by_count":9,"area":null},{"id":"2207.09150","title":"On the Usability of Transformers-based models for a French Question-Answering task","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2405.01458","title":"UQA: Corpus for Urdu Question Answering","created":"2024-05-02","cited_by_count":8,"area":null},{"id":"2104.07646","title":"Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering","created":"2021-04-15","cited_by_count":6,"area":null},{"id":"2111.01543","title":"UQuAD1.0: Development of an Urdu Question Answering Training Data for Machine Reading Comprehension","created":"2021-11-02","cited_by_count":6,"area":null},{"id":"2310.16127","title":"Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2103.09185","title":"A Multilingual African Embedding for FAQ Chatbots","created":"2021-03-16","cited_by_count":5,"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":"2205.06025","title":"DTW at Qur'an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2206.01550","title":"TCE at Qur'an QA 2022: Arabic Language Question Answering Over Holy Qur'an Using a Post-Processed Ensemble of BERT-based Models","created":"2022-06-03","cited_by_count":2,"area":null},{"id":"2407.02147","title":"GemmAr: Enhancing LLMs Through Arabic Instruction-Tuning","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2508.06971","title":"Two-Stage Quranic QA via Ensemble Retrieval and Instruction-Tuned Answer Extraction","created":"2025-08-09","cited_by_count":2,"area":null},{"id":"2111.13138","title":"TunBERT: Pretrained Contextualized Text Representation for Tunisian Dialect","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2204.09593","title":"COOL, a Context Outlooker, and its Application to Question Answering and other Natural Language Processing Tasks","created":"2022-04-01","cited_by_count":1,"area":null},{"id":"2303.03290","title":"AmQA: Amharic Question Answering Dataset","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2410.13318","title":"Computational Approaches to Arabic-English Code-Switching","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2501.05963","title":"Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2507.23404","title":"Enhanced Arabic Text Retrieval with Attentive Relevance Scoring","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2111.05671","title":"Pre-trained Transformer-Based Approach for Arabic Question Answering : A Comparative Study","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2201.09227","title":"A Large and Diverse Arabic Corpus for Language Modeling","created":"2022-01-23","cited_by_count":0,"area":null},{"id":"2309.02712","title":"Unveiling the frontiers of deep learning: innovations shaping diverse domains","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2401.03590","title":"Building Efficient and Effective OpenQA Systems for Low-Resource Languages","created":"2024-01-07","cited_by_count":0,"area":null},{"id":"2404.08617","title":"Synthetic Dataset Creation and Fine-Tuning of Transformer Models for Question Answering in Serbian","created":"2024-04-12","cited_by_count":0,"area":null},{"id":"2404.12177","title":"EuSQuAD: Automatically Translated and Aligned SQuAD2.0 for Basque","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2404.16257","title":"Translation of Multifaceted Data without Re-Training of Machine Translation Systems","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2412.20212","title":"Building a Rich Dataset to Empower the Persian Question Answering Systems","created":"2024-12-28","cited_by_count":0,"area":null}],"next_cursor":null}