{"total":152,"rows":[{"id":"2411.14198","title":"Why do language models perform worse for morphologically complex languages?","created":"2024-11-21","cited_by_count":62,"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":"2311.07978","title":"AfroBench: How Good are Large Language Models on African Languages?","created":"2023-11-14","cited_by_count":43,"area":null},{"id":"2406.03368","title":"IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models","created":"2024-06-05","cited_by_count":43,"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":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2407.08818","title":"MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization","created":"2024-07-11","cited_by_count":31,"area":null},{"id":"2401.13303","title":"MaLA-500: Massive Language Adaptation of Large Language Models","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2507.06378","title":"Evaluating Morphological Alignment of Tokenizers in 70 Languages","created":"2025-07-08","cited_by_count":22,"area":null},{"id":"2407.03994","title":"Unlocking the Potential of Model Merging for Low-Resource Languages","created":"2024-07-04","cited_by_count":19,"area":null},{"id":"2408.17024","title":"InkubaLM: A small language model for low-resource African languages","created":"2024-08-30","cited_by_count":18,"area":null},{"id":"2412.17837","title":"Evaluating the Capabilities of Large Language Models for Multi-label Emotion Understanding","created":"2024-12-17","cited_by_count":17,"area":"lr"},{"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":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2404.19159","title":"What Drives Performance in Multilingual Language Models?","created":"2024-04-29","cited_by_count":15,"area":null},{"id":"2406.19759","title":"Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment","created":"2024-06-28","cited_by_count":14,"area":null},{"id":"2410.13153","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2505.21265","title":"Multilingual Pretraining for Pixel Language Models","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2601.06395","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","created":"2026-01-10","cited_by_count":12,"area":null},{"id":"2603.19223","title":"F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World","created":"2026-03-19","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":"2404.05829","title":"SambaLingo: Teaching Large Language Models New Languages","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2406.07424","title":"MINERS: Multilingual Language Models as Semantic Retrievers","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2501.06374","title":"AFRIDOC-MT: Document-level MT Corpus for African Languages","created":"2025-01-10","cited_by_count":11,"area":null},{"id":"2501.08284","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","created":"2025-01-14","cited_by_count":11,"area":null},{"id":"2501.14491","title":"Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter","created":"2025-01-24","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":"2504.04152","title":"Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources","created":"2025-04-05","cited_by_count":10,"area":"lr"},{"id":"2506.04557","title":"SSA-COMET: Do LLMs Outperform Learned Metrics in Evaluating MT for Under-Resourced African Languages?","created":"2025-06-05","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":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","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":"2509.20045","title":"Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks","created":"2025-09-24","cited_by_count":9,"area":null},{"id":"2609.37647","title":"Evaluating and Benchmarking the System One Model Jev","created":"2026-09-29","cited_by_count":9,"area":null},{"id":"2407.02320","title":"Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2412.00948","title":"Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2507.12720","title":"FLEXITOKENS: Flexible Tokenization for Evolving Language Models","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2508.16431","title":"Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish","created":"2025-08-22","cited_by_count":8,"area":null},{"id":"2402.03782","title":"Soft Prompt Tuning for Cross-Lingual Transfer: When Less is More","created":"2024-02-06","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":"2410.09948","title":"State of NLP in Kenya: A Survey","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2412.03331","title":"LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings","created":"2024-12-04","cited_by_count":7,"area":null},{"id":"2412.08392","title":"The Roles of English in Evaluating Multilingual Language Models","created":"2024-12-11","cited_by_count":7,"area":null},{"id":"2505.14045","title":"From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2505.15935","title":"MAPS: A Multilingual Benchmark for Agent Performance and Security","created":"2025-05-21","cited_by_count":7,"area":"agents"},{"id":"2506.08400","title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2507.08538","title":"The AI Language Proficiency Monitor -- Tracking the Progress of LLMs on Multilingual Benchmarks","created":"2025-07-11","cited_by_count":7,"area":null},{"id":"2510.10062","title":"HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks","created":"2025-10-11","cited_by_count":7,"area":null},{"id":"2409.17326","title":"How Transliterations Improve Crosslingual Alignment","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2412.12500","title":"Beyond Data Quantity: Key Factors Driving Performance in Multilingual Language Models","created":"2024-12-17","cited_by_count":6,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2508.19089","title":"It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs","created":"2025-08-26","cited_by_count":6,"area":null},{"id":"2511.06531","title":"Ibom NLP: A Step Toward Inclusive Natural Language Processing for Nigeria's Minority Languages","created":"2025-11-09","cited_by_count":6,"area":null},{"id":"2405.05116","title":"XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples","created":"2024-05-08","cited_by_count":5,"area":null},{"id":"2405.13010","title":"UCCIX: Irish-eXcellence Large Language Model","created":"2024-05-13","cited_by_count":5,"area":null},{"id":"2502.11546","title":"DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2502.12852","title":"MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching","created":"2025-02-18","cited_by_count":5,"area":null},{"id":"2503.01150","title":"MiLiC-Eval: Benchmarking Multilingual LLMs for China's Minority Languages","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2404.01490","title":"AAdaM at SemEval-2024 Task 1: Augmentation and Adaptation for Multilingual Semantic Textual Relatedness","created":"2024-04-01","cited_by_count":4,"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":"2501.06117","title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","created":"2025-01-10","cited_by_count":4,"area":null},{"id":"2503.18247","title":"AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2505.13498","title":"IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluation","created":"2025-05-16","cited_by_count":4,"area":"lr"},{"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":"2605.24718","title":"The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty","created":"2026-05-23","cited_by_count":4,"area":null},{"id":"2404.03912","title":"Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2410.18902","title":"LLMs for Extremely Low-Resource Finno-Ugric Languages","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2411.05527","title":"How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP","created":"2024-11-08","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":"2504.21018","title":"HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization","created":"2025-04-21","cited_by_count":3,"area":null},{"id":"2506.12158","title":"A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2507.17578","title":"Synthetic Voice Data for Automatic Speech Recognition in African Languages","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2508.03523","title":"FilBench: Can LLMs Understand and Generate Filipino?","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2510.06730","title":"PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.19217","title":"Modality Matching Matters: Calibrating Language Distances for Cross-Lingual Transfer in URIEL+","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2510.23896","title":"AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages","created":"2025-10-27","cited_by_count":3,"area":"rag"},{"id":"2601.21665","title":"AdaptBPE: From General Purpose to Specialized Tokenizers","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2608.25089","title":"Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation","created":"2026-08-25","cited_by_count":3,"area":null},{"id":"2310.05404","title":"Exploring the Maze of Multilingual Modeling","created":"2023-10-09","cited_by_count":2,"area":null},{"id":"2404.02534","title":"ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model","created":"2024-04-03","cited_by_count":2,"area":"synth"},{"id":"2407.02147","title":"GemmAr: Enhancing LLMs Through Arabic Instruction-Tuning","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2407.14878","title":"Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment","created":"2024-07-20","cited_by_count":2,"area":null},{"id":"2408.02239","title":"Pula: Training Large Language Models for Setswana","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2409.18199","title":"LangSAMP: Language-Script Aware Multilingual Pretraining","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2506.04385","title":"MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP","created":"2025-06-04","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":"2510.07890","title":"Standard-to-Dialect Transfer Trends Differ across Text and Speech: A Case Study on Intent and Topic Classification in German Dialects","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2512.03989","title":"Teaching Old Tokenizers New Words: Efficient Tokenizer Adaptation for Pre-trained Models","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2601.05699","title":"Afri-MCQA: Multimodal Cultural Question Answering for African Languages","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2601.16278","title":"Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification","created":"2026-01-22","cited_by_count":2,"area":"synth"},{"id":"2603.20854","title":"SozKZ: Training Efficient Small Language Models for Kazakh from Scratch","created":"2026-03-21","cited_by_count":2,"area":null},{"id":"2604.16656","title":"Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2501.00874","title":"LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2503.13101","title":"Who Wrote This? Identifying Machine vs Human-Generated Text in Hausa","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2505.12116","title":"A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2505.14395","title":"MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language","created":"2025-05-20","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}],"next_cursor":"100"}