{"total":66,"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":"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":"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":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","cited_by_count":68,"area":null},{"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":"2305.16171","title":"Multi-lingual and Multi-cultural Figurative Language Understanding","created":"2023-05-25","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":"2212.10785","title":"SERENGETI: Massively Multilingual Language Models for Africa","created":"2022-12-21","cited_by_count":40,"area":null},{"id":"2401.05632","title":"Natural Language Processing for Dialects of a Language: A Survey","created":"2024-01-11","cited_by_count":40,"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":"2407.19672","title":"SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages","created":"2024-07-29","cited_by_count":36,"area":null},{"id":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2310.15135","title":"Quantifying the Dialect Gap and its Correlates Across Languages","created":"2023-10-23","cited_by_count":33,"area":null},{"id":"2401.12873","title":"Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model","created":"2024-01-23","cited_by_count":33,"area":"alignment"},{"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":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"area":null},{"id":"2304.09805","title":"A Survey of Corpora for Germanic Low-Resource Languages and Dialects","created":"2023-04-19","cited_by_count":16,"area":null},{"id":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2302.12239","title":"What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure","created":"2023-02-23","cited_by_count":13,"area":null},{"id":"2406.19564","title":"Voices Unheard: NLP Resources and Models for Yor\\`ub\\'a Regional Dialects","created":"2024-06-27","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":"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":"2503.12440","title":"HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs","created":"2025-03-16","cited_by_count":8,"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":"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":"2509.11570","title":"Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges","created":"2025-09-15","cited_by_count":6,"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":"2209.07351","title":"Rethinking Round-Trip Translation for Machine Translation Evaluation","created":"2022-09-15","cited_by_count":4,"area":null},{"id":"2308.13056","title":"Lexical Diversity in Kinship Across Languages and Dialects","created":"2023-08-24","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":"2508.07069","title":"SEADialogues: A Multilingual Culturally Grounded Multi-turn Dialogue Dataset on Southeast Asian Languages","created":"2025-08-09","cited_by_count":4,"area":null},{"id":"2404.01009","title":"Constructing and Expanding Low-Resource and Underrepresented Parallel Datasets for Indonesian Local Languages","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2408.16756","title":"How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models","created":"2024-08-29","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":"2503.03186","title":"Designing Speech Technologies for Australian Aboriginal English: Opportunities, Risks and Participation","created":"2025-03-05","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":"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":"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":"2402.13917","title":"Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2505.20445","title":"In-context Language Learning for Endangered Languages in Speech Recognition","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2512.01419","title":"Rice-VL: Evaluating Vision-Language Models for Cultural Understanding Across ASEAN Countries","created":"2025-12-01","cited_by_count":2,"area":"mllm"},{"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":"2309.08741","title":"AlbNER: A Corpus for Named Entity Recognition in Albanian","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2504.21540","title":"Improving Informally Romanized Language Identification","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2510.16928","title":"ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models","created":"2025-10-19","cited_by_count":1,"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":"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":"2501.09943","title":"Indigenous Languages Spoken in Argentina: A Survey of NLP and Speech Resources","created":"2025-01-17","cited_by_count":0,"area":null},{"id":"2506.23340","title":"Information Loss in LLMs' Multilingual Translation: The Role of Training Data, Language Proximity, and Language Family","created":"2025-06-29","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":"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":"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":"2604.11803","title":"Saar-Voice: A Multi-Speaker Saarbr\\\"ucken Dialect Speech Corpus","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.10391","title":"Phoenix-VL 1.5 Medium Technical Report","created":"2026-05-11","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":"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":"2608.30107","title":"AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP","created":"2026-08-31","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}