{"total":103,"rows":[{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243,"area":null},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168,"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":"2309.04766","title":"SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning","created":"2023-09-09","cited_by_count":94,"area":null},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"area":null},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68,"area":null},{"id":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","cited_by_count":68,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"area":null},{"id":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","cited_by_count":56,"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":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50,"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":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2204.04541","title":"KOBEST: Korean Balanced Evaluation of Significant Tasks","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2109.04607","title":"IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization","created":"2021-09-10","cited_by_count":25,"area":null},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24,"area":null},{"id":"2205.12148","title":"Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer","created":"2022-05-24","cited_by_count":22,"area":null},{"id":"2305.13627","title":"InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning","created":"2023-05-23","cited_by_count":21,"area":null},{"id":"2402.14327","title":"Subobject-level Image Tokenization","created":"2024-02-22","cited_by_count":21,"area":null},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2404.06138","title":"Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages","created":"2024-04-09","cited_by_count":18,"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":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","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":"2402.14086","title":"LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons","created":"2024-02-21","cited_by_count":11,"area":null},{"id":"2401.06034","title":"LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization","created":"2024-01-11","cited_by_count":10,"area":null},{"id":"2403.09362","title":"Komodo: A Linguistic Expedition into Indonesia's Regional Languages","created":"2024-03-14","cited_by_count":10,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2305.14716","title":"GlobalBench: A Benchmark for Global Progress in Natural Language Processing","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2403.15882","title":"VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2412.06926","title":"When Every Token Counts: Optimal Segmentation for Low-Resource Language Models","created":"2024-12-09","cited_by_count":8,"area":null},{"id":"2403.05434","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2410.04269","title":"RoQLlama: A Lightweight Romanian Adapted Language Model","created":"2024-10-05","cited_by_count":7,"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":"2504.13816","title":"Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations","created":"2025-04-18","cited_by_count":6,"area":null},{"id":"2508.12459","title":"LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages","created":"2025-08-17","cited_by_count":6,"area":null},{"id":"2108.10808","title":"Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation","created":"2021-08-24","cited_by_count":5,"area":null},{"id":"2204.06699","title":"SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study","created":"2022-04-14","cited_by_count":5,"area":null},{"id":"2209.01638","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","created":"2022-09-04","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":"2309.10661","title":"NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages","created":"2023-09-19","cited_by_count":5,"area":null},{"id":"2502.14911","title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2210.13778","title":"IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension","created":"2022-10-25","cited_by_count":4,"area":null},{"id":"2409.08564","title":"Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia","created":"2024-09-13","cited_by_count":4,"area":null},{"id":"2410.18390","title":"Monolingual and Multilingual Misinformation Detection for Low-Resource Languages: A Comprehensive Survey","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2502.18148","title":"NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous Scripts","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2107.12627","title":"Cross-lingual Transferring of Pre-trained Contextualized Language Models","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2310.14557","title":"The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2410.17532","title":"Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact","created":"2024-10-23","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":"2107.06802","title":"BERT Fine-Tuning for Sentiment Analysis on Indonesian Mobile Apps Reviews","created":"2021-07-14","cited_by_count":2,"area":null},{"id":"2203.16027","title":"Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension","created":"2022-03-30","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":"2207.10524","title":"NusaCrowd: A Call for Open and Reproducible NLP Research in Indonesian Languages","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2310.00679","title":"CebuaNER: A New Baseline Cebuano Named Entity Recognition Model","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2310.08085","title":"Low-Resource Clickbait Spoiling for Indonesian via Question Answering","created":"2023-10-12","cited_by_count":2,"area":null},{"id":"2310.11584","title":"BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languages","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2311.00958","title":"IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2403.12799","title":"Investigating Text Shortening Strategy in BERT: Truncation vs Summarization","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2504.04295","title":"Dynamic Hedging Strategies in Derivatives Markets with LLM-Driven Sentiment and News Analytics","created":"2025-04-05","cited_by_count":2,"area":null},{"id":"2206.07238","title":"Location-based Twitter Filtering for the Creation of Low-Resource Language Datasets in Indonesian Local Languages","created":"2022-06-15","cited_by_count":1,"area":null},{"id":"2206.15359","title":"Two-Stage Classifier for COVID-19 Misinformation Detection Using BERT: a Study on Indonesian Tweets","created":"2022-06-30","cited_by_count":1,"area":null},{"id":"2210.06828","title":"Rethinking Annotation: Can Language Learners Contribute?","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2211.05273","title":"BERT-Based Combination of Convolutional and Recurrent Neural Network for Indonesian Sentiment Analysis","created":"2022-11-10","cited_by_count":1,"area":null},{"id":"2211.07713","title":"How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2403.06018","title":"Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource Languages","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2409.00061","title":"Enhancing Natural Language Inference Performance with Knowledge Graph for COVID-19 Automated Fact-Checking in Indonesian Language","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2505.15090","title":"DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.01592","title":"Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2507.22159","title":"IndoPref: A Multi-Domain Pairwise Preference Dataset for Indonesian","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2509.14611","title":"Leveraging IndoBERT and DistilBERT for Indonesian Emotion Classification in E-Commerce Reviews","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2509.17317","title":"Scaling, Simplification, and Adaptation: Lessons from Pretraining on Machine-Translated Text","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2602.18788","title":"BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.26095","title":"IndoBERT-Relevancy: A Context-Conditioned Relevancy Classifier for Indonesian Text","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2102.10601","title":"Web-based Application for Detecting Indonesian Clickbait Headlines using IndoBERT","created":"2021-02-21","cited_by_count":0,"area":null},{"id":"2104.09712","title":"Problems and Countermeasures in Natural Language Processing Evaluation","created":"2021-04-20","cited_by_count":0,"area":null},{"id":"2302.00856","title":"idT5: Indonesian Version of Multilingual T5 Transformer","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2310.09736","title":"Domain-Specific Language Model Post-Training for Indonesian Financial NLP","created":"2023-10-15","cited_by_count":0,"area":null},{"id":"2310.12778","title":"Label-Aware Automatic Verbalizer for Few-Shot Text Classification","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2311.00998","title":"Replicable Benchmarking of Neural Machine Translation (NMT) on Low-Resource Local Languages in Indonesia","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2403.01817","title":"NusaBERT: Teaching IndoBERT to be Multilingual and Multicultural","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2409.15762","title":"XTRUST: On the Multilingual Trustworthiness of Large Language Models","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2506.19187","title":"Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2507.01645","title":"Adapting Language Models to Indonesian Local Languages: An Empirical Study of Language Transferability on Zero-Shot Settings","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2507.03378","title":"Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2510.20670","title":"\\textsc{CantoNLU}: A benchmark for Cantonese natural language understanding","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2601.12921","title":"Injecting Knowledge from Social Science Journals to Improve Indonesian Cultural Understanding by LLMs","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2603.26253","title":"SocialX: A Modular Platform for Multi-Source Big Data Research in Indonesia","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.07057","title":"IndoBERT-Sentiment: Context-Conditioned Sentiment Classification for Indonesian Text","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.25392","title":"Benchmarking PyCaret AutoML Against IndoBERT Fine-Tuning for Sentiment Analysis on Indonesian IKN Twitter Data","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2604.27439","title":"Sentiment Analysis of AI Adoption in Indonesian Higher Education Using Machine Learning and Transformer-Based Models","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.03439","title":"Benchmarking Logistic Regression, SVM, Naive Bayes, and IndoBERT Fine-Tuning for Sentiment Analysis on Indonesian Product Reviews","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.03443","title":"Sentiment Analysis of Indonesian Spotify Reviews Using Machine Learning and BiLSTM","created":"2026-05-05","cited_by_count":0,"area":null}],"next_cursor":"100"}