{"total":148,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2502.19634","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","created":"2025-02-26","cited_by_count":173,"area":"lr"},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110,"area":"lr"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69,"area":"moe"},{"id":"2309.06979","title":"Auto-Regressive Next-Token Predictors are Universal Learners","created":"2023-09-13","cited_by_count":67,"area":"lr"},{"id":"2404.13081","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","created":"2024-04-17","cited_by_count":67,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49,"area":"lr"},{"id":"2404.15676","title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","created":"2024-04-24","cited_by_count":48,"area":"lr"},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47,"area":"lr"},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45,"area":"lr"},{"id":"2505.20674","title":"PonderLM: Pretraining Language Models to Ponder in Continuous Space","created":"2025-05-27","cited_by_count":44,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2405.19425","title":"Adaptive In-conversation Team Building for Language Model Agents","created":"2024-05-29","cited_by_count":39,"area":"agents"},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2410.06238","title":"EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration","created":"2024-10-08","cited_by_count":34,"area":"lr"},{"id":"2406.03853","title":"Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism","created":"2024-06-06","cited_by_count":32,"area":"inference"},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2405.15574","title":"Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models","created":"2024-05-24","cited_by_count":30,"area":"ssm"},{"id":"2506.14728","title":"AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes","created":"2025-06-17","cited_by_count":30,"area":"agents"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2310.10845","title":"CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference","created":"2023-10-16","cited_by_count":27,"area":"lr"},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"area":null},{"id":"2312.05562","title":"Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models","created":"2023-12-09","cited_by_count":27,"area":"lr"},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2406.17328","title":"Dual-Space Knowledge Distillation for Large Language Models","created":"2024-06-25","cited_by_count":25,"area":"distill"},{"id":"2410.14675","title":"To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts","created":"2024-10-18","cited_by_count":25,"area":"rag"},{"id":"2308.06207","title":"Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals","created":"2023-08-11","cited_by_count":24,"area":"lr"},{"id":"2403.03348","title":"Learning to Maximize Mutual Information for Chain-of-Thought Distillation","created":"2024-03-05","cited_by_count":23,"area":"lr"},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21,"area":null},{"id":"2402.12022","title":"Distilling Large Language Models for Text-Attributed Graph Learning","created":"2024-02-19","cited_by_count":20,"area":"distill"},{"id":"2312.10730","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","created":"2023-12-17","cited_by_count":19,"area":"lr"},{"id":"2403.16385","title":"Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","created":"2024-03-25","cited_by_count":19,"area":"lr"},{"id":"2406.13555","title":"BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation","created":"2024-06-19","cited_by_count":19,"area":null},{"id":"2402.15000","title":"Divide-or-Conquer? Which Part Should You Distill Your LLM?","created":"2024-02-22","cited_by_count":17,"area":"lr"},{"id":"2409.01281","title":"Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs","created":"2024-08-25","cited_by_count":17,"area":"lr"},{"id":"2401.16553","title":"SelectLLM: Can LLMs Select Important Instructions to Annotate?","created":"2024-01-29","cited_by_count":16,"area":null},{"id":"2406.14511","title":"Investigating Mysteries of CoT-Augmented Distillation","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2410.10336","title":"CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning","created":"2024-10-14","cited_by_count":16,"area":"lr"},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"area":"lr"},{"id":"2404.00457","title":"MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks","created":"2024-03-30","cited_by_count":14,"area":null},{"id":"2405.10799","title":"Training Compute Thresholds: Features and Functions in AI Regulation","created":"2024-05-17","cited_by_count":14,"area":null},{"id":"2502.12224","title":"Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate","created":"2025-02-17","cited_by_count":13,"area":"moe"},{"id":"2310.18239","title":"Fine-Tuning Language Models Using Formal Methods Feedback","created":"2023-10-27","cited_by_count":12,"area":"alignment"},{"id":"2402.13098","title":"ELAD: Explanation-Guided Large Language Models Active Distillation","created":"2024-02-20","cited_by_count":12,"area":null},{"id":"2403.00354","title":"Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy","created":"2024-03-01","cited_by_count":12,"area":null},{"id":"2404.03414","title":"Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought","created":"2024-04-04","cited_by_count":12,"area":"lr"},{"id":"2407.03181","title":"Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs","created":"2024-07-03","cited_by_count":12,"area":"lr"},{"id":"2410.18588","title":"Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data","created":"2024-10-24","cited_by_count":12,"area":"synth"},{"id":"2502.19557","title":"Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?","created":"2025-02-26","cited_by_count":12,"area":"lr"},{"id":"2503.10167","title":"\"Well, Keep Thinking\": Enhancing LLM Reasoning with Adaptive Injection Decoding","created":"2025-03-13","cited_by_count":12,"area":"lr"},{"id":"2508.16861","title":"Learning from Diverse Reasoning Paths with Routing and Collaboration","created":"2025-08-23","cited_by_count":12,"area":"lr"},{"id":"2408.12168","title":"FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation","created":"2024-08-22","cited_by_count":11,"area":null},{"id":"2504.00424","title":"Hawkeye:Efficient Reasoning with Model Collaboration","created":"2025-04-01","cited_by_count":11,"area":"lr"},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2408.14134","title":"Exploring the Potential of Large Language Models for Heterophilic Graphs","created":"2024-08-26","cited_by_count":10,"area":null},{"id":"2502.14854","title":"CLIPPER: Compression enables long-context synthetic data generation","created":"2025-02-20","cited_by_count":10,"area":"synth"},{"id":"2311.15316","title":"Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference","created":"2023-11-26","cited_by_count":9,"area":null},{"id":"2412.11499","title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents","created":"2024-12-16","cited_by_count":9,"area":"agents"},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2403.09085","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","created":"2024-03-14","cited_by_count":8,"area":"lr"},{"id":"2408.09846","title":"Continual Dialogue State Tracking via Reason-of-Select Distillation","created":"2024-08-19","cited_by_count":8,"area":null},{"id":"2502.06659","title":"Who Taught You That? Tracing Teachers in Model Distillation","created":"2025-02-10","cited_by_count":8,"area":"distill"},{"id":"2504.11426","title":"A Dual-Space Framework for General Knowledge Distillation of Large Language Models","created":"2025-04-15","cited_by_count":8,"area":"distill"},{"id":"2505.20072","title":"Incentivizing Strong Reasoning from Weak Supervision","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2509.23574","title":"Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2509.08814","title":"Merge-of-Thought Distillation","created":"2025-09-10","cited_by_count":7,"area":"lr"},{"id":"2404.10877","title":"Incubating Text Classifiers Following User Instruction with Nothing but LLM","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2405.19635","title":"GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient Cloud-edge Collaboration LLM Deployment","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2509.05602","title":"Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation","created":"2025-09-06","cited_by_count":6,"area":"lr"},{"id":"2311.09612","title":"Efficient End-to-End Visual Document Understanding with Rationale Distillation","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2407.14477","title":"Data-Centric Human Preference with Rationales for Direct Preference Alignment","created":"2024-07-19","cited_by_count":5,"area":"alignment"},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2508.06583","title":"Discerning minds or generic tutors? Evaluating instructional guidance capabilities in Socratic LLMs","created":"2025-08-08","cited_by_count":5,"area":null},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2310.07488","title":"KwaiYiiMath: Technical Report","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2311.09613","title":"Digital Socrates: Evaluating LLMs through Explanation Critiques","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2409.10007","title":"SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL","created":"2024-09-16","cited_by_count":4,"area":"lr"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2506.06470","title":"SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2508.17590","title":"RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System","created":"2025-08-25","cited_by_count":4,"area":"agents"},{"id":"2511.07380","title":"Mining Useful General Data for Low-Resource Domain Adaptation","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2311.06383","title":"Distilling Large Language Models using Skill-Occupation Graph Context for HR-Related Tasks","created":"2023-11-10","cited_by_count":3,"area":"distill"},{"id":"2406.16672","title":"CAVE: Controllable Authorship Verification Explanations","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2510.05871","title":"Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering","created":"2025-10-07","cited_by_count":3,"area":"lr"},{"id":"2309.04663","title":"FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2402.03175","title":"Beyond the Black Box: A Statistical Model for LLM Reasoning and Inference","created":"2024-02-05","cited_by_count":2,"area":"lr"},{"id":"2402.10424","title":"Pelican Soup Framework: A Theoretical Framework for Language Model Capabilities","created":"2024-02-16","cited_by_count":2,"area":null}],"next_cursor":"100"}