{"total":91,"rows":[{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"area":null},{"id":"2401.17163","title":"Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chat","created":"2024-01-30","cited_by_count":23,"area":"agents"},{"id":"2405.20574","title":"Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark","created":"2024-05-31","cited_by_count":23,"area":null},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15,"area":null},{"id":"2305.13047","title":"Automated stance detection in complex topics and small languages: the challenging case of immigration in polarizing news media","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2306.04306","title":"Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes","created":"2023-06-07","cited_by_count":13,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2502.04362","title":"LLMs can be easily Confused by Instructional Distractions","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2212.03419","title":"JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset","created":"2022-12-07","cited_by_count":11,"area":null},{"id":"2306.07902","title":"Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark","created":"2023-06-13","cited_by_count":10,"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":"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":"2405.09913","title":"TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data","created":"2024-05-16","cited_by_count":9,"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":"2501.07482","title":"TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time","created":"2025-01-13","cited_by_count":8,"area":null},{"id":"2505.04531","title":"Overcoming Data Scarcity in Generative Language Modelling for Low-Resource Languages: A Systematic Review","created":"2025-05-07","cited_by_count":8,"area":null},{"id":"2410.10489","title":"Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation","created":"2024-10-14","cited_by_count":7,"area":null},{"id":"2411.04573","title":"Multistage Fine-tuning Strategies for Automatic Speech Recognition in Low-resource Languages","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2405.06818","title":"A Systematic Review of NLP for Ghanaian Languages: Datasets, Models, and a Research Roadmap","created":"2024-05-10","cited_by_count":5,"area":null},{"id":"2405.14446","title":"Worldwide Federated Training of Language Models","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2409.10965","title":"Cross-lingual transfer of multilingual models on low resource African Languages","created":"2024-09-17","cited_by_count":5,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2411.09073","title":"CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback","created":"2024-11-13","cited_by_count":5,"area":"alignment"},{"id":"2412.04774","title":"Foundation Models for Low-Resource Language Education (Vision Paper)","created":"2024-12-06","cited_by_count":5,"area":null},{"id":"2209.06581","title":"Applying wav2vec2 for Speech Recognition on Bengali Common Voices Dataset","created":"2022-09-11","cited_by_count":4,"area":null},{"id":"2308.02234","title":"Sinhala-English Parallel Word Dictionary Dataset","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2404.18286","title":"Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages","created":"2024-04-28","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":"2112.09860","title":"Morpheme Boundary Detection & Grammatical Feature Prediction for Gujarati : Dataset & Model","created":"2021-12-18","cited_by_count":3,"area":null},{"id":"2501.15773","title":"Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2210.05726","title":"Automatic Speech Recognition of Low-Resource Languages Based on Chukchi","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2402.10575","title":"Symbolic Autoencoding for Self-Supervised Sequence Learning","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2405.01590","title":"101 Billion Arabic Words Dataset","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2406.11028","title":"Universal Cross-Lingual Text Classification","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2412.12800","title":"Breaking the Programming Language Barrier: Multilingual Prompting to Empower Non-Native English Learners","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2412.16365","title":"Overview of the First Workshop on Language Models for Low-Resource Languages (LoResLM 2025)","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2503.11911","title":"LAG-MMLU: Benchmarking Frontier LLM Understanding in Latvian and Giriama","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2503.21393","title":"An evaluation of LLMs and Google Translate for translation of selected Indian languages via sentiment and semantic analyses","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2506.00863","title":"L3Cube-MahaEmotions: A Marathi Emotion Recognition Dataset with Synthetic Annotations using CoTR prompting and Large Language Models","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2509.08105","title":"MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning","created":"2025-09-09","cited_by_count":2,"area":"lr"},{"id":"2510.12389","title":"Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2510.16743","title":"Zero-Shot Performance Prediction for Probabilistic Scaling Laws","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2208.09180","title":"Effective Transfer Learning for Low-Resource Natural Language Understanding","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2305.03207","title":"Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2306.06077","title":"Semantically-Prompted Language Models Improve Visual Descriptions","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2309.09877","title":"Not Enough Labeled Data? Just Add Semantics: A Data-Efficient Method for Inferring Online Health Texts","created":"2023-09-18","cited_by_count":1,"area":null},{"id":"2312.15872","title":"Heterogeneous Encoders Scaling In The Transformer For Neural Machine Translation","created":"2023-12-26","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":"2411.05200","title":"Toward Cultural Interpretability: A Linguistic Anthropological Framework for Describing and Evaluating Large Language Models (LLMs)","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2412.00218","title":"NushuRescue: Revitalization of the Endangered Nushu Language with AI","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2503.17810","title":"ParsiPy: NLP Toolkit for Historical Persian Texts in Python","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2504.20022","title":"Better To Ask in English? Evaluating Factual Accuracy of Multilingual LLMs in English and Low-Resource Languages","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2509.02503","title":"L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2607.04515","title":"Towards Digital Preservation of Efik: TTS for a Low-Resource African Language","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2108.10791","title":"Ensuring the Inclusive Use of Natural Language Processing in the Global Response to COVID-19","created":"2021-08-11","cited_by_count":0,"area":null},{"id":"2205.11840","title":"Lutma: a Frame-Making Tool for Collaborative FrameNet Development","created":"2022-05-24","cited_by_count":0,"area":null},{"id":"2212.09723","title":"MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource Languages","created":"2022-12-19","cited_by_count":0,"area":null},{"id":"2306.14067","title":"UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation","created":"2023-06-24","cited_by_count":0,"area":null},{"id":"2312.16104","title":"Dotless Representation of Arabic Text: Analysis and Modeling","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2403.07947","title":"The evaluation of a code-switched Sepedi-English automatic speech recognition system","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2410.13445","title":"Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2411.00988","title":"Retrieval-enriched zero-shot image classification in low-resource domains","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2411.04316","title":"A Multilingual Sentiment Lexicon for Low-Resource Language Translation using Large Languages Models and Explainable AI","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2411.08294","title":"Collaborative Participatory Research with LLM Agents in South Asia: An Empirically-Grounded Methodological Initiative and Agenda from Field Evidence in Sri Lanka","created":"2024-11-13","cited_by_count":0,"area":"agents"},{"id":"2411.13453","title":"LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Models","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2412.13924","title":"Language verY Rare for All","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2502.16947","title":"Using Machine Learning to Detect Fraudulent SMSs in Chichewa","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2502.19784","title":"NaijaNLP: A Survey of Nigerian Low-Resource Languages","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2503.18760","title":"Synthetic Function Demonstrations Improve Generation in Low-Resource Programming Languages","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2505.01096","title":"Evaluating Vision Language Model Adaptations for Radiology Report Generation in Low-Resource Languages","created":"2025-05-02","cited_by_count":0,"area":"mllm"},{"id":"2505.07857","title":"Enhanced Urdu Intent Detection with Large Language Models and Prototype-Informed Predictive Pipelines","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2505.17371","title":"An End-to-End Approach for Child Reading Assessment in the Xhosa Language","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.17272","title":"QUST_NLP at SemEval-2025 Task 7: A Three-Stage Retrieval Framework for Monolingual and Crosslingual Fact-Checked Claim Retrieval","created":"2025-06-12","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":"2506.21563","title":"FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Models","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2506.23958","title":"Bridging the Gap with Retrieval-Augmented Generation: Making Prosthetic Device User Manuals Available in Marginalised Languages","created":"2025-06-30","cited_by_count":0,"area":"rag"},{"id":"2508.14051","title":"Benchmarking Sociolinguistic Diversity in Swahili NLP: A Taxonomy-Guided Approach","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.05729","title":"QCSE: A Pretrained Quantum Context-Sensitive Word Embedding for Natural Language Processing","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2510.05644","title":"The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.09771","title":"PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2511.09537","title":"NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in Low-Resource Languages","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2512.19379","title":"OmniMER: Auxiliary-Enhanced LLM Adaptation for Indonesian Multimodal Emotion Recognition","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2605.03799","title":"Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF","created":"2026-05-05","cited_by_count":0,"area":"rag"},{"id":"2608.04808","title":"A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.23194","title":"Enhancing speech representation learning with cross-modal knowledge transfer with HGNN under low resource settings: the case study of Yemba","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2610.15757","title":"Enhancing Zero-Shot Domain Transfer in Low-Resource Sentiment Analysis: A Case Study in Marathi","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}