{"list":"other","total":54,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2305.19860","title":"A Survey on Large Language Models for Recommendation","created":"2023-05-31","cited_by_count":379},{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316},{"id":"2410.05779","title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","created":"2024-10-08","cited_by_count":315},{"id":"2506.07044","title":"Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning","created":"2025-06-08","cited_by_count":230},{"id":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"2307.00589","title":"MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval","created":"2023-07-02","cited_by_count":185},{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163},{"id":"2406.00922","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","created":"2024-06-03","cited_by_count":154},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121},{"id":"2402.18060","title":"Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions","created":"2024-02-28","cited_by_count":109},{"id":"2411.07279","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","created":"2024-11-11","cited_by_count":96},{"id":"2212.09865","title":"Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations","created":"2022-12-19","cited_by_count":70},{"id":"2406.06331","title":"MedExQA: Medical Question Answering Benchmark with Multiple Explanations","created":"2024-06-10","cited_by_count":60},{"id":"2210.09932","title":"Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature","created":"2022-10-18","cited_by_count":55},{"id":"2408.00727","title":"Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions","created":"2024-08-01","cited_by_count":54},{"id":"2104.05767","title":"Paragraph-level Simplification of Medical Texts","created":"2021-04-12","cited_by_count":53},{"id":"2505.20633","title":"Test-Time Learning for Large Language Models","created":"2025-05-27","cited_by_count":50},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40},{"id":"2503.07459","title":"MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks","created":"2025-03-10","cited_by_count":40},{"id":"2404.18443","title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers","created":"2024-04-29","cited_by_count":38},{"id":"2505.12371","title":"MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks","created":"2025-05-18","cited_by_count":29},{"id":"2409.01980","title":"Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey","created":"2024-09-03","cited_by_count":27},{"id":"2303.07502","title":"Meta-learning approaches for few-shot learning: A survey of recent advances","created":"2023-03-13","cited_by_count":25},{"id":"2410.02551","title":"ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration","created":"2024-10-03","cited_by_count":23},{"id":"2505.14107","title":"DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models","created":"2025-05-20","cited_by_count":21},{"id":"2403.11491","title":"Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting","created":"2024-03-18","cited_by_count":20},{"id":"2403.04197","title":"Large Language Models are In-Context Molecule Learners","created":"2024-03-07","cited_by_count":18},{"id":"2505.12392","title":"SLOT: Sample-specific Language Model Optimization at Test-time","created":"2025-05-18","cited_by_count":18},{"id":"2407.15620","title":"Dual Test-time Training for Out-of-distribution Recommender System","created":"2024-07-22","cited_by_count":16},{"id":"2408.08422","title":"Assessing and Enhancing Large Language Models in Rare Disease Question-answering","created":"2024-08-15","cited_by_count":16},{"id":"2402.02212","title":"A Survey to Recent Progress Towards Understanding In-Context Learning","created":"2024-02-03","cited_by_count":14},{"id":"2508.15746","title":"End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning","created":"2025-08-21","cited_by_count":10},{"id":"2506.04611","title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","created":"2025-06-05","cited_by_count":9},{"id":"2410.21666","title":"Minimum Entropy Coupling with Bottleneck","created":"2024-10-29","cited_by_count":5},{"id":"2501.16373","title":"Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseases","created":"2025-01-23","cited_by_count":5},{"id":"2508.08730","title":"Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation","created":"2025-08-12","cited_by_count":5},{"id":"2510.02919","title":"Self-Reflective Generation at Test Time","created":"2025-10-03","cited_by_count":3},{"id":"2505.11802","title":"Diffmv: A Unified Diffusion Framework for Healthcare Predictions with Random Missing Views and View Laziness","created":"2025-05-17","cited_by_count":2},{"id":"2505.18283","title":"TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification","created":"2025-05-23","cited_by_count":2}],"next_cursor":null}