{"total":59,"rows":[{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2505.20315","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","created":"2025-05-22","cited_by_count":38,"area":"lr"},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2510.19093","title":"Weight Decay may matter more than muP for Learning Rate Transfer in Practice","created":"2025-10-21","cited_by_count":20,"area":null},{"id":"2504.16922","title":"Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2506.02918","title":"World Modelling Improves Language Model Agents","created":"2025-06-03","cited_by_count":14,"area":"wm"},{"id":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2507.14783","title":"Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling","created":"2025-07-20","cited_by_count":10,"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":"2504.17720","title":"Multilingual Performance Biases of Large Language Models in Education","created":"2025-04-24","cited_by_count":9,"area":null},{"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":"2505.19978","title":"DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2509.11414","title":"Continually Adding New Languages to Multilingual Language Models","created":"2025-09-14","cited_by_count":7,"area":null},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2602.14763","title":"Unlocking Reasoning Capability on Machine Translation in Large Language Models","created":"2026-02-16","cited_by_count":6,"area":"lr"},{"id":"2505.17083","title":"Scale-invariant Attention","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2506.01872","title":"Is Extending Modality The Right Path Towards Omni-Modality?","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2509.21459","title":"A State-of-the-Art SQL Reasoning Model using RLVR","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2511.21437","title":"A Systematic Study of In-the-Wild Model Merging for Large Language Models","created":"2025-11-26","cited_by_count":5,"area":null},{"id":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2511.13254","title":"Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2601.09473","title":"SimMerge: Learning to Select Merge Operators from Similarity Signals","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2602.13274","title":"ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2505.11081","title":"ShiQ: Bringing back Bellman to LLMs","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2505.19116","title":"Controlling Language Confusion in Multilingual LLMs","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2506.14794","title":"Assembly of Experts: Linear-time construction of the Chimera LLM variants with emergent and adaptable behaviors","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2507.04416","title":"RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2604.09544","title":"Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types","created":"2026-04-10","cited_by_count":3,"area":"safety"},{"id":"2604.17609","title":"Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity","created":"2026-04-19","cited_by_count":3,"area":"agents"},{"id":"2606.07874","title":"Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators","created":"2026-06-05","cited_by_count":3,"area":null},{"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":"2510.04686","title":"How does the optimizer implicitly bias the model merging loss landscape?","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2511.08605","title":"Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2602.12323","title":"The Appeal and Reality of Recycling LoRAs with Adaptive Merging","created":"2026-02-12","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":"2602.18196","title":"RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference","created":"2026-02-20","cited_by_count":2,"area":"inference"},{"id":"2605.19010","title":"AgentNLQ: A General-Purpose Agent for Natural Language to SQL","created":"2026-05-18","cited_by_count":2,"area":"agents"},{"id":"2603.04532","title":"Still Fresh? Evaluating Temporal Drift in Retrieval Benchmarks","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.15773","title":"Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.18019","title":"BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2606.24281","title":"CALIBER: Calibrating Confidence Before and After Reasoning in Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2606.31648","title":"Think in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using Agents","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2609.04173","title":"Last Translation Benchmark","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2505.18331","title":"PerMedCQA: Benchmarking Large Language Models on Medical Consumer Question Answering in Persian Language","created":"2025-05-23","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"},{"id":"2512.01067","title":"On The Finetuning of MLIPs Through the Lens of Iterated Maps With BPTT","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2603.18788","title":"Mi:dm K 2.5 Pro","created":"2026-03-19","cited_by_count":0,"area":"agents"},{"id":"2604.03374","title":"CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2604.24645","title":"K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology","created":"2026-04-27","cited_by_count":0,"area":"lr"},{"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":"2609.13916","title":"North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)","created":"2026-09-12","cited_by_count":0,"area":"moe"},{"id":"2609.33204","title":"Turning Speech Language Models into Multilingual Listeners","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.03199","title":"Predicting and Repairing Merge Collapse in Large Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.09152","title":"sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}