{"total":68,"rows":[{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894,"area":"lr"},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"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":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","cited_by_count":68,"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":"2303.13592","title":"Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages","created":"2023-03-23","cited_by_count":51,"area":null},{"id":"2305.14288","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","created":"2023-05-23","cited_by_count":51,"area":"lr"},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"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":"2404.01854","title":"IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces","created":"2024-04-02","cited_by_count":39,"area":"lr"},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2402.17302","title":"Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese","created":"2024-02-27","cited_by_count":36,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2311.09205","title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27,"area":null},{"id":"2304.08865","title":"Romanization-based Large-scale Adaptation of Multilingual Language Models","created":"2023-04-18","cited_by_count":21,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2502.14301","title":"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models","created":"2025-02-20","cited_by_count":19,"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":"2305.10971","title":"NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2409.12958","title":"MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions","created":"2024-09-19","cited_by_count":12,"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":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2510.10159","title":"BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data","created":"2025-10-11","cited_by_count":10,"area":null},{"id":"2406.12739","title":"Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages","created":"2024-06-18","cited_by_count":9,"area":"distill"},{"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":"2210.13838","title":"Multilingual Relation Classification via Efficient and Effective Prompting","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2311.09404","title":"To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages","created":"2023-11-15","cited_by_count":7,"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":"2409.18193","title":"GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge","created":"2024-09-26","cited_by_count":7,"area":null},{"id":"2410.22660","title":"Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models","created":"2024-10-30","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":"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":"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":"2510.07037","title":"Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2602.13139","title":"OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report","created":"2026-02-13","cited_by_count":5,"area":null},{"id":"2410.21573","title":"Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense","created":"2024-10-28","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":"2505.17795","title":"DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2506.12450","title":"Language Surgery in Multilingual Large Language Models","created":"2025-06-14","cited_by_count":4,"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":"2501.06892","title":"Language Fusion for Parameter-Efficient Cross-lingual Transfer","created":"2025-01-12","cited_by_count":3,"area":null},{"id":"2502.10140","title":"Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages","created":"2025-02-14","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":"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":"2311.07820","title":"On the Analysis of Cross-Lingual Prompt Tuning for Decoder-based Multilingual Model","created":"2023-11-14","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":"2604.11490","title":"Anthropogenic Regional Adaptation in Multimodal Vision-Language Model","created":"2026-04-13","cited_by_count":2,"area":"mllm"},{"id":"2304.04703","title":"Transfer Learning for Low-Resource Sentiment Analysis","created":"2023-04-10","cited_by_count":1,"area":null},{"id":"2306.14517","title":"Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition","created":"2023-06-26","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":"2603.10006","title":"Adaptive Engram Memory System for Indonesian Language Model: Generative AI Based on TOBA LM for Batak and Minang Language","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2609.29511","title":"EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation","created":"2026-08-25","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":"2306.12693","title":"Multilingual Neural Machine Translation System for Indic to Indic Languages","created":"2023-06-22","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":"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":"2509.05060","title":"Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2601.08146","title":"Beyond Transfer Accuracy: Mechanism-Guided Controlled Adaptation for Low-Resource Languages","created":"2026-01-13","cited_by_count":0,"area":"mechinterp"},{"id":"2604.17134","title":"RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2606.11786","title":"Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.28715","title":"SEATauBench: Progressively Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.21016","title":"CultureTalk-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages","created":"2026-07-23","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}