{"total":58,"rows":[{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"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":"2305.15011","title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","created":"2023-05-24","cited_by_count":81,"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":"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":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53,"area":"lr"},{"id":"2104.05882","title":"Discourse Probing of Pretrained Language Models","created":"2021-04-13","cited_by_count":38,"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":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"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":"2211.06993","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","created":"2022-11-13","cited_by_count":24,"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":"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":"2310.08102","title":"QASiNa: Religious Domain Question Answering using Sirah Nabawiyah","created":"2023-10-12","cited_by_count":15,"area":null},{"id":"2106.01478","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","created":"2021-06-02","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":"2202.13558","title":"CINO: A Chinese Minority Pre-trained Language Model","created":"2022-02-28","cited_by_count":11,"area":null},{"id":"2311.05746","title":"Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models","created":"2023-11-09","cited_by_count":11,"area":"mllm"},{"id":"2504.06011","title":"Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2312.01314","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","created":"2023-12-03","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":"2305.07491","title":"A Comprehensive Analysis of Adapter Efficiency","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2506.02280","title":"The State of Large Language Models for African Languages: Progress and Challenges","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2402.02113","title":"Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon","created":"2024-02-03","cited_by_count":7,"area":null},{"id":"2201.00558","title":"Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models","created":"2022-01-03","cited_by_count":5,"area":"distill"},{"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":"2311.12405","title":"IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages","created":"2023-11-21","cited_by_count":5,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","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":"2205.12394","title":"MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification","created":"2022-05-24","cited_by_count":3,"area":null},{"id":"2306.11341","title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2410.03182","title":"Generating bilingual example sentences with large language models as lexicography assistants","created":"2024-10-04","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":"2412.01186","title":"SailCompass: Towards Reproducible and Robust Evaluation for Southeast Asian Languages","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2506.07506","title":"What Do Indonesians Really Need from Language Technology? A Nationwide Survey","created":"2025-06-09","cited_by_count":3,"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":"2508.12243","title":"SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?","created":"2025-08-17","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":"2210.06828","title":"Rethinking Annotation: Can Language Learners Contribute?","created":"2022-10-13","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":"2403.14990","title":"MasonTigers at SemEval-2024 Task 1: An Ensemble Approach for Semantic Textual Relatedness","created":"2024-03-22","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":"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":"2410.23133","title":"Crowdsourcing Lexical Diversity","created":"2024-10-30","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":"2304.02746","title":"Sejarah dan Perkembangan Teknik Natural Language Processing (NLP) Bahasa Indonesia: Tinjauan tentang sejarah, perkembangan teknologi, dan aplikasi NLP dalam bahasa Indonesia","created":"2023-03-28","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":"2403.12563","title":"Simple Hack for Transformers against Heavy Long-Text Classification on a Time- and Memory-Limited GPU Service","created":"2024-03-19","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":"2510.21068","title":"Bridging Language Gaps with Adaptive RAG: Improving Indonesian Language Question Answering","created":"2025-10-24","cited_by_count":0,"area":"rag"},{"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":"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":"2605.04885","title":"A Comparative Study of PyCaret AutoML and CNN-BiLSTM for Binary Hate Speech Detection in Indonesian Twitter","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2610.14112","title":"Does System One Transfer? Calibrated Typed-Decision Models, Label Budgets, and Translation for Indonesian Regional Languages","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}