{"total":124,"rows":[{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"area":"synth"},{"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":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703,"area":"lr"},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383,"area":null},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329,"area":"lr"},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284,"area":"lr"},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251,"area":"lr"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2212.00193","title":"Distilling Reasoning Capabilities into Smaller Language Models","created":"2022-12-01","cited_by_count":158,"area":"lr"},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"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":"2307.11768","title":"Question Decomposition Improves the Faithfulness of Model-Generated Reasoning","created":"2023-07-17","cited_by_count":108,"area":"lr"},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105,"area":"lr"},{"id":"2305.09656","title":"SatLM: Satisfiability-Aided Language Models Using Declarative Prompting","created":"2023-05-16","cited_by_count":102,"area":"lr"},{"id":"2310.20689","title":"Learning From Mistakes Makes LLM Better Reasoner","created":"2023-10-31","cited_by_count":101,"area":"lr"},{"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":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2309.06979","title":"Auto-Regressive Next-Token Predictors are Universal Learners","created":"2023-09-13","cited_by_count":67,"area":"lr"},{"id":"2305.18395","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":64,"area":"lr"},{"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":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56,"area":"lr"},{"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":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2408.15881","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","created":"2024-08-28","cited_by_count":45,"area":"mllm"},{"id":"2402.05445","title":"Accurate LoRA-Finetuning Quantization of LLMs via Information Retention","created":"2024-02-08","cited_by_count":41,"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":"2404.10346","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","created":"2024-04-16","cited_by_count":31,"area":"lr"},{"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":"2405.20535","title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning","created":"2024-05-30","cited_by_count":31,"area":"lr"},{"id":"2506.14728","title":"AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes","created":"2025-06-17","cited_by_count":30,"area":"agents"},{"id":"2305.14386","title":"Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation","created":"2023-05-22","cited_by_count":29,"area":null},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2303.07616","title":"The Life Cycle of Knowledge in Big Language Models: A Survey","created":"2023-03-14","cited_by_count":23,"area":null},{"id":"2407.15248","title":"XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models","created":"2024-07-21","cited_by_count":23,"area":null},{"id":"2405.07551","title":"MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning","created":"2024-05-13","cited_by_count":22,"area":"lr"},{"id":"2402.12022","title":"Distilling Large Language Models for Text-Attributed Graph Learning","created":"2024-02-19","cited_by_count":20,"area":"distill"},{"id":"2502.17898","title":"VeriPlan: Integrating Formal Verification and LLMs into End-User Planning","created":"2025-02-25","cited_by_count":20,"area":null},{"id":"2408.10548","title":"Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution","created":"2024-08-20","cited_by_count":19,"area":null},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2404.14604","title":"Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training","created":"2024-04-22","cited_by_count":17,"area":"lr"},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"area":"lr"},{"id":"2311.04929","title":"An Interdisciplinary Outlook on Large Language Models for Scientific Research","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15,"area":null},{"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":"2310.06547","title":"Rationale-Enhanced Language Models are Better Continual Relation Learners","created":"2023-10-10","cited_by_count":13,"area":null},{"id":"2302.04813","title":"Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting","created":"2023-02-09","cited_by_count":12,"area":"lr"},{"id":"2312.15033","title":"Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention","created":"2023-12-22","cited_by_count":12,"area":null},{"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":"2503.04872","title":"TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2305.12723","title":"Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2406.12442","title":"Abstraction-of-Thought Makes Language Models Better Reasoners","created":"2024-06-18","cited_by_count":11,"area":"lr"},{"id":"2506.05947","title":"IntentionESC: An Intention-Centered Framework for Enhancing Emotional Support in Dialogue Systems","created":"2025-06-06","cited_by_count":11,"area":null},{"id":"2605.12483","title":"Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training","created":"2026-05-12","cited_by_count":11,"area":"lr"},{"id":"2403.19167","title":"Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering","created":"2024-03-28","cited_by_count":10,"area":"lr"},{"id":"2502.16612","title":"MemeIntel: Explainable Detection of Propagandistic and Hateful Memes","created":"2025-02-23","cited_by_count":10,"area":null},{"id":"2405.10860","title":"ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains","created":"2024-05-17","cited_by_count":9,"area":"lr"},{"id":"2407.02340","title":"RVISA: Reasoning and Verification for Implicit Sentiment Analysis","created":"2024-07-02","cited_by_count":9,"area":"lr"},{"id":"2412.13942","title":"A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2405.13014","title":"QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models","created":"2024-05-14","cited_by_count":8,"area":null},{"id":"2406.11275","title":"Self-training Large Language Models through Knowledge Detection","created":"2024-06-17","cited_by_count":8,"area":"synth"},{"id":"2309.11439","title":"Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction","created":"2023-09-20","cited_by_count":7,"area":null},{"id":"2405.19795","title":"SLM as Guardian: Pioneering AI Safety with Small Language Models","created":"2024-05-30","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":"2305.07280","title":"Harvesting Event Schemas from Large Language Models","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2312.04087","title":"VRPTEST: Evaluating Visual Referring Prompting in Large Multimodal Models","created":"2023-12-07","cited_by_count":6,"area":"mllm"},{"id":"2406.16203","title":"LLMs' Classification Performance is Overclaimed","created":"2024-06-23","cited_by_count":6,"area":null},{"id":"2409.13733","title":"RNR: Teaching Large Language Models to Follow Roles and Rules","created":"2024-09-10","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":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2305.11480","title":"CCGen: Explainable Complementary Concept Generation in E-Commerce","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2403.05584","title":"Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention","created":"2024-03-03","cited_by_count":5,"area":null},{"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":"2501.09804","title":"Enhancing Generalization in Chain of Thought Reasoning for Smaller Models","created":"2025-01-16","cited_by_count":5,"area":"lr"},{"id":"2509.23619","title":"Reasoning Scaffolding: Distilling the Flow of Thought from LLMs","created":"2025-09-28","cited_by_count":5,"area":"lr"},{"id":"2310.07488","title":"KwaiYiiMath: Technical Report","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2409.12586","title":"Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights","created":"2024-09-19","cited_by_count":4,"area":"distill"},{"id":"2409.17870","title":"Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores","created":"2024-09-26","cited_by_count":4,"area":"inference"},{"id":"2504.05625","title":"Model-Agnostic Policy Explanations with Large Language Models","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2505.22848","title":"LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2605.23158","title":"What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference","created":"2026-05-22","cited_by_count":4,"area":null},{"id":"2309.10346","title":"Explaining Agent Behavior with Large Language Models","created":"2023-09-19","cited_by_count":3,"area":"agents"},{"id":"2311.08213","title":"Unlock the Power: Competitive Distillation for Multi-Modal Large Language Models","created":"2023-11-14","cited_by_count":3,"area":"mllm"},{"id":"2311.18062","title":"Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation","created":"2023-11-29","cited_by_count":3,"area":"agents"},{"id":"2406.12169","title":"Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval","created":"2024-06-18","cited_by_count":3,"area":"rag"},{"id":"2406.16672","title":"CAVE: Controllable Authorship Verification Explanations","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2411.02664","title":"Explanations that reveal all through the definition of encoding","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2309.04663","title":"FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2311.07556","title":"Using Natural Language Explanations to Improve Robustness of In-context Learning","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2401.03158","title":"CoT-Driven Framework for Short Text Classification: Enhancing and Transferring Capabilities from Large to Smaller Model","created":"2024-01-06","cited_by_count":2,"area":null},{"id":"2403.15886","title":"Leveraging Zero-Shot Prompting for Efficient Language Model Distillation","created":"2024-03-23","cited_by_count":2,"area":"distill"}],"next_cursor":"100"}