{"total":86,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793,"area":"mllm"},{"id":"2412.04261","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","created":"2024-12-05","cited_by_count":129,"area":null},{"id":"2502.10361","title":"Enhancing Multilingual LLM Pretraining with Model-Based Data Selection","created":"2025-02-14","cited_by_count":35,"area":null},{"id":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2504.10356","title":"MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages","created":"2025-04-14","cited_by_count":26,"area":null},{"id":"2502.07346","title":"BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models","created":"2025-02-11","cited_by_count":23,"area":null},{"id":"2605.11887","title":"Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models","created":"2026-05-12","cited_by_count":21,"area":"mechinterp"},{"id":"2504.10191","title":"Localized Cultural Knowledge is Conserved and Controllable in Large Language Models","created":"2025-04-14","cited_by_count":20,"area":"wm"},{"id":"2508.04796","title":"Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization","created":"2025-08-06","cited_by_count":20,"area":null},{"id":"2506.19468","title":"MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages","created":"2025-06-24","cited_by_count":15,"area":null},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2606.06712","title":"Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation","created":"2026-06-04","cited_by_count":11,"area":"diffusion"},{"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":"2510.25947","title":"Revisiting Multilingual Data Mixtures in Language Model Pretraining","created":"2025-10-29","cited_by_count":10,"area":null},{"id":"2510.01146","title":"mR3: Multilingual Rubric-Agnostic Reward Reasoning Models","created":"2025-10-01","cited_by_count":8,"area":"lr"},{"id":"2509.05209","title":"Hunyuan-MT Technical Report","created":"2025-09-05","cited_by_count":7,"area":null},{"id":"2511.01066","title":"HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models","created":"2025-11-02","cited_by_count":7,"area":null},{"id":"2605.08738","title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","created":"2026-05-09","cited_by_count":7,"area":"moe"},{"id":"2509.03162","title":"SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala","created":"2025-09-03","cited_by_count":6,"area":"lr"},{"id":"2601.11579","title":"Bielik 11B v3: Multilingual Large Language Model for European Languages","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2603.17102","title":"Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency","created":"2026-03-17","cited_by_count":6,"area":"moe"},{"id":"2510.19806","title":"The Art of Asking: Multilingual Prompt Optimization for Synthetic Data","created":"2025-10-22","cited_by_count":5,"area":"synth"},{"id":"2412.14471","title":"Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2507.22752","title":"CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2509.21294","title":"UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2509.25543","title":"Aligning Multilingual Reasoning with Verifiable Semantics from a High-Resource Expert Model","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2512.20757","title":"TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2603.11881","title":"Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language","created":"2026-03-12","cited_by_count":4,"area":"distill"},{"id":"2604.19292","title":"Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2607.25614","title":"MemSFT: Mitigating Alignment Tax with an External Parametric Memory","created":"2026-07-28","cited_by_count":3,"area":"alignment"},{"id":"2607.28109","title":"Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2510.05291","title":"Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2602.16811","title":"Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2604.12911","title":"Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2503.23714","title":"Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.22777","title":"MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2508.02635","title":"Test Set Quality in Multilingual LLM Evaluation","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2511.03180","title":"BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culture","created":"2025-11-05","cited_by_count":1,"area":"lr"},{"id":"2602.03709","title":"No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2604.19262","title":"CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2604.20225","title":"The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.15990","title":"Defining Cultural Capabilities for AI Evaluation: A Taxonomy Grounded in Intercultural Communication Theory","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.25360","title":"Learning to Route Languages for Multilingual Policy Optimization","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.01995","title":"CARTE: A Benchmark for Mapping Language Model Knowledge Across France","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.07020","title":"MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation Insights","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2609.11505","title":"Structural priors for data-efficient language learning","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2610.02293","title":"HakemBench: A Turkish Benchmark of Typed Decisions","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2508.13526","title":"MATA: Mindful Assessment of the Telugu Abilities of Large Language Models","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.15556","title":"Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2512.21580","title":"Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.04632","title":"From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.10804","title":"BYOL: Bring Your Own Language Into LLMs","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.11200","title":"FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2601.16803","title":"SoS: Analysis of Surface over Semantics in Multilingual Text-To-Image Generation","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2603.24826","title":"Synthetic Rewriting as a Quality Multiplier: Evidence from Portuguese Continued Pretraining","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.03374","title":"CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2604.14448","title":"MARCA: A Checklist-Based Benchmark for Multilingual Web Search","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.07093","title":"The Translation Tax Is Not a Scalar: A Counterfactual Audit of English-Source Cue Inheritance in Chinese Multilingual Benchmarks","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.07533","title":"Why do Large Language Models Fail in Low-resource Translation? Unraveling the Token Dynamics of Large Language Models for Machine Translation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.07731","title":"Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs","created":"2026-05-08","cited_by_count":0,"area":"moe"},{"id":"2605.26293","title":"CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2605.28163","title":"DEPART: DEcomposing PARiTy across Multilingual LLMs","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.29897","title":"ExCAM: Explainable Cultural Awareness Metrics","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30481","title":"When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.07167","title":"UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.07422","title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.21869","title":"The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.27595","title":"Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.00724","title":"MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.00890","title":"MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.01395","title":"Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.09925","title":"From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.15535","title":"L3Cube-IndicQuest v2: A Large-Scale Multilingual Benchmark for Evaluating Factual Knowledge of Large Language Models Across Indic Languages","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.03350","title":"From Zero to Hero: An Open LLM Ecosystem for Armenian","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.07971","title":"MeRoTune: RoPE-Safe Merging with a Tunable Dial","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.30535","title":"Feeding BabyLMs Macaroni: Code-Switching Curricula Cause Cross-Lingual Convergence","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.40181","title":"Index-Translate: A Multilingual Translation Model Family -- Text, Speech, Controlled Dubbing, and Long-Document Translation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01921","title":"Cross-Lingual Alignment for Decoder-Only Models using MoE Routers","created":"2026-10-01","cited_by_count":0,"area":"moe"},{"id":"2610.05084","title":"Towards cross-cultural study of folksong lyrics with machine translation","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.11585","title":"Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.17959","title":"Virtual Head Attention","created":"2026-10-13","cited_by_count":0,"area":"moe"},{"id":"2610.19704","title":"BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20102","title":"Language Exposure Matters: Distribution and Order in Multilingual BabyLM Pre-training","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20472","title":"ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}