{"total":138,"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":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212,"area":"lr"},{"id":"2504.07934","title":"SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement","created":"2025-04-10","cited_by_count":145,"area":"lr"},{"id":"2506.13759","title":"Discrete Diffusion in Large Language and Multimodal Models: A Survey","created":"2025-06-16","cited_by_count":61,"area":"mllm"},{"id":"2402.10110","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","created":"2024-02-15","cited_by_count":57,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2506.11116","title":"Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models","created":"2025-06-09","cited_by_count":50,"area":null},{"id":"2407.06645","title":"Entropy Law: The Story Behind Data Compression and LLM Performance","created":"2024-07-09","cited_by_count":44,"area":null},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41,"area":null},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"area":null},{"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":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"id":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2503.02197","title":"ATLaS: Agent Tuning via Learning Critical Steps","created":"2025-03-04","cited_by_count":31,"area":"agents"},{"id":"2406.04845","title":"FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models","created":"2024-06-07","cited_by_count":30,"area":null},{"id":"2407.15235","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","created":"2024-07-21","cited_by_count":30,"area":null},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2408.08072","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","created":"2024-08-15","cited_by_count":27,"area":null},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"id":"2502.17514","title":"SAE-V: Interpreting Multimodal Models for Enhanced Alignment","created":"2025-02-22","cited_by_count":23,"area":"mllm"},{"id":"2410.07672","title":"MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization","created":"2024-10-10","cited_by_count":22,"area":"agents"},{"id":"2503.11441","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","created":"2025-03-14","cited_by_count":21,"area":null},{"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":"2407.05040","title":"Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruning","created":"2024-07-06","cited_by_count":20,"area":null},{"id":"2409.08813","title":"Your Weak LLM is Secretly a Strong Teacher for Alignment","created":"2024-09-13","cited_by_count":20,"area":"alignment"},{"id":"2601.09195","title":"ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection","created":"2026-01-14","cited_by_count":18,"area":null},{"id":"2411.07133","title":"Stronger Models are NOT Stronger Teachers for Instruction Tuning","created":"2024-11-11","cited_by_count":16,"area":null},{"id":"2508.03550","title":"Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations","created":"2025-08-05","cited_by_count":15,"area":"alignment"},{"id":"2510.26374","title":"BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning","created":"2025-10-30","cited_by_count":14,"area":"alignment"},{"id":"2410.15225","title":"Chasing Random: Instruction Selection Strategies Fail to Generalize","created":"2024-10-19","cited_by_count":13,"area":null},{"id":"2501.18578","title":"R.I.P.: Better Models by Survival of the Fittest Prompts","created":"2025-01-30","cited_by_count":13,"area":null},{"id":"2502.04380","title":"Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2505.07437","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning","created":"2025-05-12","cited_by_count":13,"area":"alignment"},{"id":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2406.14115","title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models","created":"2024-06-20","cited_by_count":12,"area":"lr"},{"id":"2502.05075","title":"Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension","created":"2025-02-07","cited_by_count":12,"area":null},{"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":"2504.13835","title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space","created":"2025-04-18","cited_by_count":12,"area":null},{"id":"2505.13893","title":"InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2505.18710","title":"GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis","created":"2025-05-24","cited_by_count":12,"area":"rag"},{"id":"2406.15938","title":"RuleR: Improving LLM Controllability by Rule-based Data Recycling","created":"2024-06-22","cited_by_count":11,"area":null},{"id":"2410.05725","title":"KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server","created":"2024-10-08","cited_by_count":11,"area":"distill"},{"id":"2410.10926","title":"Federated Data-Efficient Instruction Tuning for Large Language Models","created":"2024-10-14","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":"2405.13578","title":"ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2601.22588","title":"Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"area":null},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2505.17266","title":"Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"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":"2509.02492","title":"GRAM-R$^2$: Self-Training Generative Foundation Reward Models for Reward Reasoning","created":"2025-09-02","cited_by_count":7,"area":"alignment"},{"id":"2511.07074","title":"Importance-Aware Data Selection for Efficient LLM Instruction Tuning","created":"2025-11-10","cited_by_count":7,"area":null},{"id":"2601.23155","title":"SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training","created":"2026-01-30","cited_by_count":7,"area":null},{"id":"2406.10882","title":"SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models","created":"2024-06-16","cited_by_count":6,"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":"2503.01836","title":"CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom","created":"2025-03-03","cited_by_count":6,"area":"synth"},{"id":"2503.02359","title":"Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2511.04671","title":"X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations","created":"2025-11-06","cited_by_count":6,"area":"diffusion"},{"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":"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":"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":"2501.02795","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","created":"2025-01-06","cited_by_count":5,"area":"lr"},{"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":"2410.12621","title":"Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning","created":"2024-10-16","cited_by_count":4,"area":"lr"},{"id":"2410.13804","title":"BenTo: Benchmark Task Reduction with In-Context Transferability","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2412.14809","title":"ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis","created":"2024-12-19","cited_by_count":4,"area":"synth"},{"id":"2504.14810","title":"DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2508.18142","title":"Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation","created":"2025-08-25","cited_by_count":4,"area":"alignment"},{"id":"2511.07380","title":"Mining Useful General Data for Low-Resource Domain Adaptation","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2604.07892","title":"Data Selection for Multi-turn Dialogue Instruction Tuning","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2605.14967","title":"InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2408.05541","title":"P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training","created":"2024-08-10","cited_by_count":3,"area":null},{"id":"2410.10901","title":"3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection","created":"2024-10-13","cited_by_count":3,"area":null},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"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":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2603.00846","title":"Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models","created":"2026-03-01","cited_by_count":3,"area":"rag"},{"id":"2604.10448","title":"Instruction Data Selection via Answer Divergence","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2605.30334","title":"Demystifying Data Organization for Enhanced LLM Training","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2406.04371","title":"Phased Instruction Fine-Tuning for Large Language Models","created":"2024-06-01","cited_by_count":2,"area":null},{"id":"2412.15652","title":"Error-driven Data-efficient Large Multimodal Model Tuning","created":"2024-12-20","cited_by_count":2,"area":"mllm"},{"id":"2502.18978","title":"Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2505.12300","title":"HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2508.20083","title":"DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version)","created":"2025-08-27","cited_by_count":2,"area":"rag"},{"id":"2509.24005","title":"Does Weak-to-strong Generalization Happen under Spurious Correlations?","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2605.05742","title":"Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.27354","title":"Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders","created":"2026-05-26","cited_by_count":2,"area":"mechinterp"},{"id":"2605.29229","title":"Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2606.19549","title":"Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2609.09075","title":"ThinkPrior: Zero-Rollout Difficulty Priors for Cold-Start Prompt Selection in RLVR","created":"2026-09-08","cited_by_count":2,"area":"lr"},{"id":"2403.19340","title":"Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models","created":"2024-03-28","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":"2501.07959","title":"Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning","created":"2025-01-14","cited_by_count":1,"area":"synth"},{"id":"2502.04797","title":"Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks","created":"2025-02-07","cited_by_count":1,"area":null}],"next_cursor":"100"}