{"total":57,"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":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84,"area":null},{"id":"2502.19613","title":"Self-rewarding correction for mathematical reasoning","created":"2025-02-26","cited_by_count":70,"area":"lr"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"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":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2410.09008","title":"SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction","created":"2024-10-11","cited_by_count":40,"area":"lr"},{"id":"2405.10467","title":"Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents","created":"2024-05-16","cited_by_count":35,"area":"agents"},{"id":"2402.10614","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","created":"2024-02-16","cited_by_count":34,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2503.02197","title":"ATLaS: Agent Tuning via Learning Critical Steps","created":"2025-03-04","cited_by_count":31,"area":"agents"},{"id":"2605.13255","title":"Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning","created":"2026-05-13","cited_by_count":23,"area":"lr"},{"id":"2503.17439","title":"LEMMA: Learning from Errors for MatheMatical Advancement in LLMs","created":"2025-03-21","cited_by_count":21,"area":"lr"},{"id":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","cited_by_count":21,"area":"alignment"},{"id":"2504.04974","title":"Towards Visual Text Grounding of Multimodal Large Language Model","created":"2025-04-07","cited_by_count":18,"area":"mllm"},{"id":"2411.07133","title":"Stronger Models are NOT Stronger Teachers for Instruction Tuning","created":"2024-11-11","cited_by_count":16,"area":null},{"id":"2408.12483","title":"Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation","created":"2024-08-22","cited_by_count":14,"area":null},{"id":"2411.14497","title":"Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning","created":"2024-11-21","cited_by_count":14,"area":"agents"},{"id":"2405.13448","title":"Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning","created":"2024-05-22","cited_by_count":13,"area":null},{"id":"2601.14249","title":"Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment","created":"2026-01-20","cited_by_count":13,"area":"lr"},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2502.17701","title":"From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs","created":"2025-02-24","cited_by_count":12,"area":null},{"id":"2406.15938","title":"RuleR: Improving LLM Controllability by Rule-based Data Recycling","created":"2024-06-22","cited_by_count":11,"area":null},{"id":"2404.16766","title":"Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2410.10926","title":"Federated Data-Efficient Instruction Tuning for Large Language Models","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2504.15027","title":"DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models","created":"2025-04-21","cited_by_count":10,"area":null},{"id":"2405.13326","title":"Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning","created":"2024-05-22","cited_by_count":9,"area":"synth"},{"id":"2410.04717","title":"$\\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2410.14745","title":"Semi-supervised Fine-tuning for Large Language Models","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2501.09368","title":"Aligning Instruction Tuning with Pre-training","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2503.01052","title":"ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation","created":"2025-03-02","cited_by_count":7,"area":null},{"id":"2508.21589","title":"Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning","created":"2025-08-29","cited_by_count":7,"area":null},{"id":"2410.13464","title":"IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2410.13852","title":"Retrospective Learning from Interactions","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2507.05288","title":"A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models","created":"2025-07-05","cited_by_count":6,"area":null},{"id":"2412.12865","title":"Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models","created":"2024-12-17","cited_by_count":5,"area":"alignment"},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2507.01785","title":"MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2406.16229","title":"Multi-Objective Linguistic Control of Large Language Models","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2503.00034","title":"MergeIT: From Selection to Merging for Efficient Instruction Tuning","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2505.05327","title":"RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2412.16686","title":"NILE: Internal Consistency Alignment in Large Language Models","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2502.17439","title":"Large Language Models as Realistic Microservice Trace Generators","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2507.14481","title":"DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2405.19787","title":"From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2412.17365","title":"Boosting LLM via Learning from Data Iteratively and Selectively","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2505.14752","title":"LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2511.01354","title":"Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series","created":"2025-11-03","cited_by_count":0,"area":"lr"},{"id":"2511.06776","title":"Data Trajectory Alignment for LLM Domain Adaptation: A Two-Phase Synthesis Framework for Telecommunications Mathematics","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2605.16302","title":"Reducing Credit Assignment Variance via Counterfactual Reasoning Paths","created":"2026-04-20","cited_by_count":0,"area":"lr"},{"id":"2607.16227","title":"LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.28908","title":"Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.38142","title":"AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2610.00949","title":"PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}