{"list":"other","total":59,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"2501.04519","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","created":"2025-01-08","cited_by_count":313},{"id":"2503.07365","title":"MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning","created":"2025-03-10","cited_by_count":303},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125},{"id":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119},{"id":"2502.18080","title":"Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning","created":"2025-02-25","cited_by_count":119},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113},{"id":"2405.18357","title":"Faithful Logical Reasoning via Symbolic Chain-of-Thought","created":"2024-05-28","cited_by_count":100},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96},{"id":"2306.03030","title":"Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset","created":"2023-06-05","cited_by_count":91},{"id":"2305.15269","title":"Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples","created":"2023-05-24","cited_by_count":84},{"id":"2504.05185","title":"Concise Reasoning via Reinforcement Learning","created":"2025-04-07","cited_by_count":79},{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69},{"id":"2305.14825","title":"Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners","created":"2023-05-24","cited_by_count":63},{"id":"2505.13308","title":"Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space","created":"2025-05-19","cited_by_count":43},{"id":"2503.21676","title":"How do language models learn facts? Dynamics, curricula and hallucinations","created":"2025-03-27","cited_by_count":37},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29},{"id":"2402.11442","title":"Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs","created":"2024-02-18","cited_by_count":28},{"id":"2502.06563","title":"Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation","created":"2025-02-10","cited_by_count":28},{"id":"2412.08972","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","created":"2024-12-12","cited_by_count":27},{"id":"2309.01538","title":"ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning","created":"2023-09-04","cited_by_count":26},{"id":"2408.10455","title":"IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction","created":"2024-08-19","cited_by_count":22},{"id":"2408.15778","title":"LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models","created":"2024-08-28","cited_by_count":19},{"id":"2402.10400","title":"Chain of Logic: Rule-Based Reasoning with Large Language Models","created":"2024-02-16","cited_by_count":18},{"id":"2410.02108","title":"ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement","created":"2024-10-03","cited_by_count":18},{"id":"2408.13654","title":"Symbolic Working Memory Enhances Language Models for Complex Rule Application","created":"2024-08-24","cited_by_count":17},{"id":"2411.14318","title":"Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training","created":"2024-11-21","cited_by_count":12},{"id":"2505.16475","title":"ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection","created":"2025-05-22","cited_by_count":12},{"id":"2410.08126","title":"Mars: Situated Inductive Reasoning in an Open-World Environment","created":"2024-10-10","cited_by_count":11},{"id":"2504.13227","title":"DIDS: Domain Impact-aware Data Sampling for Large Language Model Training","created":"2025-04-17","cited_by_count":4},{"id":"2503.11336","title":"Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models","created":"2025-03-14","cited_by_count":3},{"id":"2406.16293","title":"Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels","created":"2024-06-24","cited_by_count":2},{"id":"2501.01246","title":"Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion","created":"2025-01-02","cited_by_count":2}],"next_cursor":null}