{"total":77,"rows":[{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"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":"2502.17184","title":"Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2410.09335","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","created":"2024-10-12","cited_by_count":22,"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":"2503.07478","title":"VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models","created":"2025-03-10","cited_by_count":19,"area":"lr"},{"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":"2404.08029","title":"A Multi-Expert Large Language Model Architecture for Verilog Code Generation","created":"2024-04-11","cited_by_count":15,"area":null},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"id":"2409.07045","title":"Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2410.15225","title":"Chasing Random: Instruction Selection Strategies Fail to Generalize","created":"2024-10-19","cited_by_count":13,"area":null},{"id":"2502.04362","title":"LLMs can be easily Confused by Instructional Distractions","created":"2025-02-05","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":"2410.03083","title":"Scaling Parameter-Constrained Language Models with Quality Data","created":"2024-10-04","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":"2502.00245","title":"Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion","created":"2025-02-01","cited_by_count":11,"area":"synth"},{"id":"2410.10926","title":"Federated Data-Efficient Instruction Tuning for Large Language Models","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2412.00631","title":"ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning","created":"2024-12-01","cited_by_count":10,"area":null},{"id":"2503.01076","title":"Active Learning for Direct Preference Optimization","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2602.17835","title":"Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning","created":"2026-02-19","cited_by_count":10,"area":null},{"id":"2510.25817","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2408.13467","title":"LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs","created":"2024-08-24","cited_by_count":8,"area":null},{"id":"2503.09223","title":"LREF: A Novel LLM-based Relevance Framework for E-commerce","created":"2025-03-12","cited_by_count":8,"area":null},{"id":"2602.18584","title":"GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry","created":"2026-02-20","cited_by_count":8,"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":"2511.07074","title":"Importance-Aware Data Selection for Efficient LLM Instruction Tuning","created":"2025-11-10","cited_by_count":7,"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":"2410.10392","title":"Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search","created":"2024-10-14","cited_by_count":5,"area":"alignment"},{"id":"2507.15112","title":"Distributional Machine Unlearning via Selective Data Removal","created":"2025-07-20","cited_by_count":5,"area":"safety"},{"id":"2509.21499","title":"On Code-Induced Reasoning in LLMs","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2405.16579","title":"Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity","created":"2024-05-26","cited_by_count":4,"area":null},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2502.14560","title":"Less is More: Improving LLM Alignment via Preference Data Selection","created":"2025-02-20","cited_by_count":4,"area":"alignment"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2505.22076","title":"ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2602.03075","title":"ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution","created":"2026-02-03","cited_by_count":4,"area":null},{"id":"2406.07288","title":"Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models","created":"2024-06-11","cited_by_count":3,"area":null},{"id":"2410.05248","title":"SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe","created":"2024-10-07","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":"2508.19996","title":"ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2510.07118","title":"TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning","created":"2025-10-08","cited_by_count":3,"area":"alignment"},{"id":"2604.10448","title":"Instruction Data Selection via Answer Divergence","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2504.05050","title":"Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models","created":"2025-04-07","cited_by_count":2,"area":"alignment"},{"id":"2505.21191","title":"Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities","created":"2025-05-27","cited_by_count":2,"area":"moe"},{"id":"2509.13790","title":"Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2510.16806","title":"Computational Budget Should Be Considered in Data Selection","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2601.11019","title":"Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs","created":"2026-01-16","cited_by_count":2,"area":"mechinterp"},{"id":"2602.11089","title":"DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2603.14239","title":"QiMeng-CodeV-SVA: Training Specialized LLMs for Hardware Assertion Generation via RTL-Grounded Bidirectional Data Synthesis","created":"2026-03-15","cited_by_count":2,"area":"synth"},{"id":"2607.29175","title":"Execution-First Synthetic Tool-Use Trace Generation for LLM Agents","created":"2026-07-31","cited_by_count":2,"area":"agents"},{"id":"2402.14002","title":"Hallucinations or Attention Misdirection? The Path to Strategic Value Extraction in Business Using Large Language Models","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2410.00558","title":"AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation","created":"2024-10-01","cited_by_count":1,"area":"distill"},{"id":"2410.11540","title":"Data Quality Control in Federated Instruction-tuning of Large Language Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2411.06175","title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs","created":"2024-11-09","cited_by_count":1,"area":null},{"id":"2503.04807","title":"Call for Rigor in Reporting Quality of Instruction Tuning Data","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2510.13892","title":"The Harder The Better: Maintaining Supervised Fine-tuning Generalization with Less but Harder Data","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2602.00885","title":"Reliability-Aware Determinantal Point Processes for Robust Informative Data Selection in Large Language Models","created":"2026-01-31","cited_by_count":1,"area":"inference"},{"id":"2603.13201","title":"Neuron-Aware Data Selection In Instruction Tuning For Large Language Models","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2605.22205","title":"Skill Weaving: Efficient LLM Improvement via Modular Skillpacks","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2402.03049","title":"EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2407.01046","title":"FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in Large Language Models","created":"2024-07-01","cited_by_count":0,"area":"lr"},{"id":"2408.02861","title":"A Framework for Fine-Tuning LLMs using Heterogeneous Feedback","created":"2024-08-05","cited_by_count":0,"area":"alignment"},{"id":"2502.15724","title":"Instruction-Based Fine-tuning of Open-Source LLMs for Predicting Customer Purchase Behaviors","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2506.21564","title":"Team QUST at SemEval-2025 Task 10: Evaluating Large Language Models in Multiclass Multi-label Classification of News Entity Framing","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2509.06463","title":"Accelerate Scaling of LLM Finetuning via Quantifying the Coverage and Depth of Instruction Set","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2601.12807","title":"Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs","created":"2026-01-19","cited_by_count":0,"area":"lr"},{"id":"2604.10666","title":"Omnimodal Dataset Distillation via High-order Proxy Alignment","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.17384","title":"Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion","created":"2026-04-19","cited_by_count":0,"area":"safety"},{"id":"2604.26170","title":"EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.09404","title":"Let the Target Select for Itself: Data Selection via Target-Aligned Paths","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.11189","title":"A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.01104","title":"CausalMix: Data Mixture as Causal Inference for Language Model Training","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.05913","title":"Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language Models","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2610.00436","title":"Every Batch Is Its Own Validation Set: Leave-One-Out Gradient Matching for Online Data Selection in LLM Fine-Tuning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03702","title":"LESSER: Post-Training Data Selection with Output-Layer Gradients","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}