{"total":158,"rows":[{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735,"area":"synth"},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427,"area":"lr"},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2310.13023","title":"GraphGPT: Graph Instruction Tuning for Large Language Models","created":"2023-10-19","cited_by_count":226,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2402.11187","title":"LaCo: Large Language Model Pruning via Layer Collapse","created":"2024-02-17","cited_by_count":126,"area":null},{"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":"2402.16914","title":"DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers","created":"2024-02-25","cited_by_count":101,"area":"alignment"},{"id":"2311.09469","title":"Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs","created":"2023-11-16","cited_by_count":98,"area":null},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"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":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2402.16024","title":"HiGPT: Heterogeneous Graph Language Model","created":"2024-02-25","cited_by_count":45,"area":null},{"id":"2402.01620","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","created":"2024-02-02","cited_by_count":43,"area":"lr"},{"id":"2410.09918","title":"Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces","created":"2024-10-13","cited_by_count":43,"area":"lr"},{"id":"2308.08614","title":"Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought","created":"2023-08-16","cited_by_count":41,"area":"lr"},{"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":"2502.18001","title":"Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning","created":"2025-02-25","cited_by_count":40,"area":"lr"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","cited_by_count":30,"area":null},{"id":"2506.14728","title":"AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes","created":"2025-06-17","cited_by_count":30,"area":"agents"},{"id":"2311.07961","title":"The ART of LLM Refinement: Ask, Refine, and Trust","created":"2023-11-14","cited_by_count":29,"area":null},{"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":"2312.06876","title":"Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks","created":"2023-12-11","cited_by_count":27,"area":null},{"id":"2410.06215","title":"DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback","created":"2024-10-08","cited_by_count":25,"area":"agents"},{"id":"2502.01694","title":"Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation","created":"2025-02-02","cited_by_count":25,"area":"lr"},{"id":"2504.13146","title":"Antidistillation Sampling","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2402.12022","title":"Distilling Large Language Models for Text-Attributed Graph Learning","created":"2024-02-19","cited_by_count":20,"area":"distill"},{"id":"2403.04780","title":"Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining","created":"2024-03-02","cited_by_count":20,"area":null},{"id":"2408.09169","title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","created":"2024-08-17","cited_by_count":20,"area":null},{"id":"2405.16856","title":"Can We Trust LLMs? Mitigate Overconfidence Bias in LLMs through Knowledge Transfer","created":"2024-05-27","cited_by_count":19,"area":null},{"id":"2505.14582","title":"Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning","created":"2025-05-20","cited_by_count":19,"area":"lr"},{"id":"2402.01729","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2309.13075","title":"SCREWS: A Modular Framework for Reasoning with Revisions","created":"2023-09-20","cited_by_count":16,"area":"lr"},{"id":"2406.14511","title":"Investigating Mysteries of CoT-Augmented Distillation","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2510.10925","title":"Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation","created":"2025-10-13","cited_by_count":15,"area":"synth"},{"id":"2405.19737","title":"Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation","created":"2024-05-30","cited_by_count":14,"area":"lr"},{"id":"2410.03663","title":"Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review","created":"2024-10-04","cited_by_count":14,"area":"lr"},{"id":"2310.13332","title":"Democratizing Reasoning Ability: Tailored Learning from Large Language Model","created":"2023-10-20","cited_by_count":13,"area":"lr"},{"id":"2404.09170","title":"Distilling Reasoning Ability from Large Language Models with Adaptive Thinking","created":"2024-04-14","cited_by_count":13,"area":"lr"},{"id":"2506.07851","title":"Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning","created":"2025-06-09","cited_by_count":13,"area":"inference"},{"id":"2304.11872","title":"Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM","created":"2023-04-24","cited_by_count":12,"area":"synth"},{"id":"2402.13098","title":"ELAD: Explanation-Guided Large Language Models Active Distillation","created":"2024-02-20","cited_by_count":12,"area":null},{"id":"2403.01106","title":"Distilling Text Style Transfer With Self-Explanation From LLMs","created":"2024-03-02","cited_by_count":12,"area":null},{"id":"2406.05322","title":"Teaching-Assistant-in-the-Loop: Improving Knowledge Distillation from Imperfect Teacher Models in Low-Budget Scenarios","created":"2024-06-08","cited_by_count":12,"area":"distill"},{"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":"2306.04347","title":"World Models for Math Story Problems","created":"2023-06-07","cited_by_count":11,"area":null},{"id":"2410.01727","title":"Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2501.08248","title":"Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models","created":"2025-01-14","cited_by_count":11,"area":"lr"},{"id":"2508.16695","title":"Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?","created":"2025-08-21","cited_by_count":11,"area":"lr"},{"id":"2403.10351","title":"TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2506.03541","title":"Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement","created":"2025-06-04","cited_by_count":10,"area":"lr"},{"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,"area":"lr"},{"id":"2312.05795","title":"Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup","created":"2023-12-10","cited_by_count":8,"area":"mllm"},{"id":"2403.14312","title":"ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting","created":"2024-03-21","cited_by_count":8,"area":"lr"},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","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":"2505.13792","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2506.03616","title":"Learning to Insert [PAUSE] Tokens for Better Reasoning","created":"2025-06-04","cited_by_count":8,"area":"lr"},{"id":"2310.04003","title":"The Role of Federated Learning in a Wireless World with Foundation Models","created":"2023-10-06","cited_by_count":7,"area":null},{"id":"2404.15190","title":"Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following","created":"2024-04-21","cited_by_count":7,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2504.09802","title":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","created":"2025-04-14","cited_by_count":7,"area":"lr"},{"id":"2509.21282","title":"It's Not You, It's Clipping: A Soft Trust-Region via Probability Smoothing for LLM RL","created":"2025-09-25","cited_by_count":7,"area":"lr"},{"id":"2604.07774","title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2606.01476","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification","created":"2026-05-31","cited_by_count":7,"area":"lr"},{"id":"2310.05161","title":"Recurrent Neural Language Models as Probabilistic Finite-state Automata","created":"2023-10-08","cited_by_count":6,"area":null},{"id":"2406.09330","title":"Learning from Natural Language Explanations for Generalizable Entity Matching","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2410.18574","title":"SIKeD: Self-guided Iterative Knowledge Distillation for mathematical reasoning","created":"2024-10-24","cited_by_count":6,"area":"lr"},{"id":"2510.00931","title":"Making, not Taking, the Best of N","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2303.04555","title":"Streaming Kernel PCA Algorithm With Small Space","created":"2023-03-08","cited_by_count":5,"area":null},{"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":"2401.09407","title":"Deciphering Textual Authenticity: A Generalized Strategy through the Lens of Large Language Semantics for Detecting Human vs. Machine-Generated Text","created":"2024-01-17","cited_by_count":5,"area":null},{"id":"2406.13114","title":"Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation","created":"2024-06-19","cited_by_count":5,"area":"distill"},{"id":"2409.03381","title":"CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks","created":"2024-09-05","cited_by_count":5,"area":"synth"},{"id":"2409.13697","title":"Prompt Baking","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2501.09804","title":"Enhancing Generalization in Chain of Thought Reasoning for Smaller Models","created":"2025-01-16","cited_by_count":5,"area":"lr"},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2411.13045","title":"Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning","created":"2024-11-20","cited_by_count":4,"area":"distill"},{"id":"2502.16806","title":"CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers","created":"2025-02-24","cited_by_count":4,"area":"lr"},{"id":"2505.21250","title":"ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.07751","title":"AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2511.05528","title":"SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2512.00862","title":"HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs","created":"2025-11-30","cited_by_count":4,"area":null},{"id":"2402.01812","title":"Distilling LLMs' Decomposition Abilities into Compact Language Models","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2405.13004","title":"MathDivide: Improved mathematical reasoning by large language models","created":"2024-05-12","cited_by_count":3,"area":"lr"},{"id":"2407.00997","title":"Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components","created":"2024-07-01","cited_by_count":3,"area":null},{"id":"2412.15750","title":"Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference","created":"2024-12-20","cited_by_count":3,"area":"mechinterp"},{"id":"2501.17905","title":"DReSS: Data-driven Regularized Structured Streamlining for Large Language Models","created":"2025-01-29","cited_by_count":3,"area":null},{"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,"area":"lr"},{"id":"2504.20946","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","created":"2025-04-29","cited_by_count":3,"area":"lr"},{"id":"2506.20480","title":"GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching","created":"2025-06-25","cited_by_count":3,"area":null}],"next_cursor":"100"}