{"total":129,"rows":[{"id":"2504.02768","title":"MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs","created":"2025-04-03","cited_by_count":71,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2502.02481","title":"Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study","created":"2025-02-04","cited_by_count":38,"area":null},{"id":"2503.12854","title":"Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation","created":"2025-03-17","cited_by_count":37,"area":"lr"},{"id":"2505.12201","title":"How Reliable is Multilingual LLM-as-a-Judge?","created":"2025-05-18","cited_by_count":30,"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":"2502.04314","title":"BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation","created":"2025-02-06","cited_by_count":22,"area":null},{"id":"2502.11175","title":"Investigating Language Preference of Multilingual RAG Systems","created":"2025-02-16","cited_by_count":22,"area":"rag"},{"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":"2502.14301","title":"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models","created":"2025-02-20","cited_by_count":19,"area":null},{"id":"2502.12788","title":"Commonsense Reasoning in Arab Culture","created":"2025-02-18","cited_by_count":16,"area":"lr"},{"id":"2503.14603","title":"Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2505.18152","title":"Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2604.18572","title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","created":"2026-04-20","cited_by_count":16,"area":null},{"id":"2503.10688","title":"CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understanding","created":"2025-03-12","cited_by_count":14,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2505.18383","title":"NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communities","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2507.22887","title":"Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning","created":"2025-07-30","cited_by_count":13,"area":null},{"id":"2510.17489","title":"DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning","created":"2025-10-20","cited_by_count":12,"area":null},{"id":"2502.08779","title":"BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models","created":"2025-02-12","cited_by_count":11,"area":"mllm"},{"id":"2505.10740","title":"SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval","created":"2025-05-15","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":"2508.08287","title":"Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2510.24081","title":"Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures","created":"2025-10-28","cited_by_count":10,"area":"lr"},{"id":"2511.21322","title":"TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories","created":"2025-11-26","cited_by_count":10,"area":null},{"id":"2505.18356","title":"The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs","created":"2025-05-23","cited_by_count":9,"area":"lr"},{"id":"2506.20544","title":"When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs","created":"2025-06-25","cited_by_count":9,"area":"lr"},{"id":"2602.05879","title":"EuroLLM-22B: Technical Report","created":"2026-02-05","cited_by_count":9,"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":"2506.01920","title":"From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2507.08924","title":"From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2510.21954","title":"Model-Aware Tokenizer Transfer","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"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":"2502.14911","title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","created":"2025-02-19","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":"2506.01675","title":"Cross-Lingual Transfer of Cultural Knowledge: An Asymmetric Phenomenon","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2506.02591","title":"On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures","created":"2025-06-03","cited_by_count":5,"area":"lr"},{"id":"2506.12388","title":"Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model","created":"2025-06-14","cited_by_count":5,"area":"moe"},{"id":"2507.22603","title":"BALSAM: A Platform for Benchmarking Arabic Large Language Models","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2508.07902","title":"Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2510.09051","title":"Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation","created":"2025-10-10","cited_by_count":5,"area":"synth"},{"id":"2604.12378","title":"ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance","created":"2026-04-14","cited_by_count":5,"area":"lr"},{"id":"2502.06394","title":"SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2505.14990","title":"Language Specific Knowledge: Do Models Know Better in X than in English?","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.16000","title":"Leveraging Online Data to Enhance Medical Knowledge in a Small Persian Language Model","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.17784","title":"EXECUTE: A Multilingual Benchmark for LLM Token Understanding","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":"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":"2603.13045","title":"Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation","created":"2026-03-13","cited_by_count":4,"area":"alignment"},{"id":"2501.05122","title":"Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model","created":"2025-01-09","cited_by_count":3,"area":"mllm"},{"id":"2502.11364","title":"Blessing of Multilinguality: A Systematic Analysis of Multilingual In-Context Learning","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2503.23088","title":"UNITYAI-GUARD: Pioneering Toxicity Detection Across Low-Resource Indian Languages","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2506.06775","title":"They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2508.17953","title":"Understanding Subword Compositionality of Large Language Models","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2509.14504","title":"Introducing OmniGEC: A Silver Multilingual Dataset for Grammatical Error Correction","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2510.23070","title":"Quality-Aware Translation Tagging in Multilingual RAG system","created":"2025-10-27","cited_by_count":3,"area":"rag"},{"id":"2512.24572","title":"Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs' Legal Reasoning Capabilities","created":"2025-12-31","cited_by_count":3,"area":"lr"},{"id":"2601.20858","title":"When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2604.24470","title":"Zero-shot Large Language Models for Automatic Readability Assessment","created":"2026-04-27","cited_by_count":3,"area":null},{"id":"2605.24048","title":"Mixture of Complementary Agents for Robust LLM Ensemble","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2606.03043","title":"The Geometry of LLM-as-Judge: Why Inter-LLM Consensus Is Not Human Alignment","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2412.09587","title":"OpenNER 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50+ Languages","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2503.04827","title":"Preserving Cultural Identity with Context-Aware Translation Through Multi-Agent AI Systems","created":"2025-03-05","cited_by_count":2,"area":"agents"},{"id":"2503.11280","title":"High-Dimensional Interlingual Representations of Large Language Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2503.23687","title":"MKA: Leveraging Cross-Lingual Consensus for Model Abstention","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2505.21171","title":"M-Wanda: Improving One-Shot Pruning for Multilingual LLMs","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2505.21941","title":"Test-Time Scaling with Repeated Sampling Improves Multilingual Text Generation","created":"2025-05-28","cited_by_count":2,"area":"lr"},{"id":"2506.14702","title":"Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2507.00999","title":"La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2508.17948","title":"Debiasing Multilingual LLMs in Cross-lingual Latent Space","created":"2025-08-25","cited_by_count":2,"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":"2510.20059","title":"Enhancing Reasoning Skills in Small Persian Medical Language Models Can Outperform Large-Scale Data Training","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2601.21000","title":"UrduBench: An Urdu Reasoning Benchmark using Contextually Ensembled Translations with Human-in-the-Loop","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"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":"2608.28860","title":"Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops","created":"2026-08-28","cited_by_count":2,"area":null},{"id":"2504.09753","title":"Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance","created":"2025-04-13","cited_by_count":1,"area":null},{"id":"2505.16385","title":"Semantic Pivots Enable Cross-Lingual Transfer in Large Language Models","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.20793","title":"Multi-lingual Functional Evaluation for Large Language Models","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2507.13238","title":"Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluation","created":"2025-07-17","cited_by_count":1,"area":"lr"},{"id":"2508.10137","title":"mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning","created":"2025-08-13","cited_by_count":1,"area":"lr"},{"id":"2509.15811","title":"Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning","created":"2025-09-19","cited_by_count":1,"area":"lr"},{"id":"2510.09189","title":"LLaMAX2: Your Translation-Enhanced Model also Performs Well in Reasoning","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2510.17476","title":"Zoom In Disparities in Healthcare LLM Q&A","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2601.17173","title":"Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","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":"2606.24964","title":"Evidence for feature-specific error correction in LLMs","created":"2026-06-23","cited_by_count":1,"area":"mechinterp"},{"id":"2608.00582","title":"Writing-System-Level Tokenizer Adaptation for Byte-Level BPE","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2608.09766","title":"Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.11110","title":"Actions Speak Louder than Words: Measuring Cross-Lingual Policy Retention in Tool-Using Agents","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2412.12956","title":"SnakModel: Lessons Learned from Training an Open Danish Large Language Model","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2502.16901","title":"Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs","created":"2025-02-24","cited_by_count":0,"area":"safety"},{"id":"2504.16627","title":"TIFIN India at SemEval-2025: Harnessing Translation to Overcome Multilingual IR Challenges in Fact-Checked Claim Retrieval","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2505.16036","title":"OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.16814","title":"Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.22542","title":"A Benchmark Dataset and Evaluation Framework for Vietnamese Large Language Models in Customer Support","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2510.15561","title":"Finetuning LLMs for EvaCun 2025 token prediction shared task","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.22616","title":"PerCoR: Evaluating Commonsense Reasoning in Persian via Multiple-Choice Sentence Completion","created":"2025-10-26","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}