{"list":"other","total":59,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"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":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"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":"2506.13131","title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","created":"2025-06-16","cited_by_count":867},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"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":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2502.18864","title":"Accelerating scientific discovery with Co-Scientist","created":"2025-02-26","cited_by_count":401},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259},{"id":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231},{"id":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","cited_by_count":195},{"id":"2505.11831","title":"ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems","created":"2025-05-17","cited_by_count":190},{"id":"2006.08381","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","created":"2020-06-15","cited_by_count":161},{"id":"2501.06186","title":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs","created":"2025-01-10","cited_by_count":147},{"id":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136},{"id":"2502.07640","title":"Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving","created":"2025-02-11","cited_by_count":133},{"id":"2412.09078","title":"Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning","created":"2024-12-12","cited_by_count":110},{"id":"2212.05767","title":"A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal","created":"2022-12-12","cited_by_count":106},{"id":"2502.03544","title":"Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2","created":"2025-02-05","cited_by_count":97},{"id":"2202.13296","title":"Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering","created":"2022-02-27","cited_by_count":93},{"id":"2310.14558","title":"AlpaCare:Instruction-tuned Large Language Models for Medical Application","created":"2023-10-23","cited_by_count":90},{"id":"2410.01707","title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","created":"2024-10-02","cited_by_count":64},{"id":"2001.11850","title":"Efficient Probabilistic Logic Reasoning with Graph Neural Networks","created":"2020-01-29","cited_by_count":50},{"id":"2503.04550","title":"Benchmarking Reasoning Robustness in Large Language Models","created":"2025-03-06","cited_by_count":30},{"id":"2004.06015","title":"Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks","created":"2020-04-13","cited_by_count":25},{"id":"2407.10194","title":"Curriculum Learning for Small Code Language Models","created":"2024-07-14","cited_by_count":22},{"id":"2410.04660","title":"KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA","created":"2024-10-07","cited_by_count":20},{"id":"2405.00099","title":"Creative Beam Search: LLM-as-a-Judge For Improving Response Generation","created":"2024-04-30","cited_by_count":14},{"id":"2502.15401","title":"Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning","created":"2025-02-21","cited_by_count":12},{"id":"2410.21728","title":"Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models","created":"2024-10-29","cited_by_count":4},{"id":"2505.12495","title":"KG-MuLQA: A Framework for KG-based Multi-Level QA Extraction and Long-Context LLM Evaluation","created":"2025-05-18","cited_by_count":2},{"id":"2505.11643","title":"Can an Easy-to-Hard Curriculum Make Reasoning Emerge in Small Language Models? Evidence from a Four-Stage Curriculum on GPT-2","created":"2025-05-16","cited_by_count":1}],"next_cursor":null}