{"total":79,"rows":[{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"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":"2510.00526","title":"Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum","created":"2025-10-01","cited_by_count":18,"area":null},{"id":"2507.17476","title":"MultiNRC: A Challenging and Native Multilingual Reasoning Evaluation Benchmark for LLMs","created":"2025-07-23","cited_by_count":16,"area":"lr"},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","cited_by_count":15,"area":"alignment"},{"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":"2510.27269","title":"Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?","created":"2025-10-31","cited_by_count":12,"area":"lr"},{"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":"2512.24618","title":"Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models","created":"2025-12-31","cited_by_count":10,"area":"agents"},{"id":"2602.05879","title":"EuroLLM-22B: Technical Report","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2509.23657","title":"Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2505.18102","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2508.17162","title":"Quantifying Language Disparities in Multilingual Large Language Models","created":"2025-08-23","cited_by_count":7,"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":"2602.12135","title":"WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Models","created":"2026-02-12","cited_by_count":6,"area":"lr"},{"id":"2511.05901","title":"Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations","created":"2025-11-08","cited_by_count":5,"area":"rag"},{"id":"2602.01797","title":"ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routing","created":"2026-02-02","cited_by_count":5,"area":"lr"},{"id":"2602.05940","title":"R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning","created":"2026-02-05","cited_by_count":5,"area":"lr"},{"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":"2601.17383","title":"Physical Prompt Injection Attacks on Large Vision-Language Models","created":"2026-01-24","cited_by_count":4,"area":"mllm"},{"id":"2606.23165","title":"The Language Blind Spot: How Query Language and Brand Recognition Tier Shape AI-Constructed Brand Reputation Across Twelve European Languages","created":"2026-06-22","cited_by_count":4,"area":null},{"id":"2505.16591","title":"Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2507.11939","title":"POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering","created":"2025-07-16","cited_by_count":3,"area":"mllm"},{"id":"2605.22567","title":"LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2511.09373","title":"Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2511.10664","title":"Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2601.08267","title":"Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2601.18129","title":"Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2604.15490","title":"Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch","created":"2026-04-16","cited_by_count":2,"area":"lr"},{"id":"2606.15345","title":"Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus","created":"2026-06-13","cited_by_count":2,"area":"agents"},{"id":"2607.00485","title":"Efficient Multilingual Reasoning Transfer via Progressive Code-Switching","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2608.08775","title":"OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"id":"2508.04963","title":"A Metric for MLLM Alignment in Large-scale Recommendation","created":"2025-08-07","cited_by_count":1,"area":"mllm"},{"id":"2509.06401","title":"Do LLMs exhibit the same commonsense capabilities across languages?","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2510.06014","title":"ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models","created":"2025-10-07","cited_by_count":1,"area":"lr"},{"id":"2510.24450","title":"Charting the European LLM Benchmarking Landscape: A New Taxonomy and a Set of Best Practices","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.04077","title":"The truth is no diaper: Human and AI-generated associations to emotional words","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2601.15337","title":"Language Models Entangle Language and Culture","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2603.02041","title":"EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2604.20090","title":"Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2608.30052","title":"The Language of the Question Selects the Market: Query Language and Exit IP as Separable Factors in Commercial Recommendations from a Generative Search Interface","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2504.10982","title":"Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs","created":"2025-04-15","cited_by_count":0,"area":"rag"},{"id":"2507.01853","title":"Eka-Eval: An Evaluation Framework for Low-Resource Multilingual Large Language Models","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2509.22768","title":"ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.06847","title":"OpenJAI-v1.0: An Open Thai Large Language Model","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2512.10104","title":"Phishing Email Detection Using Large Language Models","created":"2025-12-10","cited_by_count":0,"area":"safety"},{"id":"2512.24867","title":"Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements","created":"2025-12-31","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":"2602.10732","title":"Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling","created":"2026-02-11","cited_by_count":0,"area":"lr"},{"id":"2602.11674","title":"Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.17283","title":"Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.22497","title":"Rashid: A Cipher-Based Framework for Exploring In-Context Language Learning","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.26511","title":"AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.28213","title":"\\textit{Versteasch du mi?} Computational and Socio-Linguistic Perspectives on GenAI, LLMs, and Non-Standard Language","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.04120","title":"Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression","created":"2026-04-05","cited_by_count":0,"area":"lr"},{"id":"2604.06903","title":"Is Biomedical Specialization Still Worth It? Insights from Domain-Adaptive Language Modelling with a New French Health Corpus","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.20720","title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.20738","title":"RespondeoQA: a Benchmark for Bilingual Latin-English Question Answering","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.14040","title":"Physics-R1: An Audited Olympiad Corpus and Released Verifiers for Visual Physics Reasoning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.27015","title":"PersLitEval: Fine-grained Benchmark and Evaluation of LLMs on Persian Literature Questions","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.27984","title":"KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2605.30107","title":"Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30685","title":"How Early Adopters Used Generative AI Worldwide: Variation by Country Income and Language","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2605.30788","title":"XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.06327","title":"Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2607.27497","title":"SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2608.09941","title":"The Multilingual Quantization Tax: Structural Collapse and Typological Fragility in Edge SLMs","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2608.30462","title":"Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.10758","title":"Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in Urdu","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.26097","title":"One Domain, Many Tongues: Composing Domain and Language LoRAs for Cross-Lingual Remote-Sensing MLLMs without Paired Data","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2609.35378","title":"Multilinguality in Hybrid Attention LLMs","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"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":"2610.04295","title":"Language-Conditioned Token and Reasoning Efficiency in Large Language Models: A Paired Cross-Lingual Study Protocol","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.15578","title":"Towards Robust Calibration Dataset for Domain-General Mixture of Experts Pruning","created":"2026-10-11","cited_by_count":0,"area":"moe"},{"id":"2610.16755","title":"The Multilingual Artificial Hivemind: Do All LLMs Think Alike in Every Language?","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.17456","title":"Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.19741","title":"Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}