{"total":100,"rows":[{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76,"area":null},{"id":"2504.13161","title":"Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training","created":"2025-04-17","cited_by_count":66,"area":null},{"id":"2506.05316","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","created":"2025-06-05","cited_by_count":56,"area":"lr"},{"id":"2505.20161","title":"Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","cited_by_count":37,"area":null},{"id":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2409.16986","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","created":"2024-09-25","cited_by_count":34,"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":"2506.11300","title":"Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning","created":"2025-06-12","cited_by_count":26,"area":null},{"id":"2501.12147","title":"Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities","created":"2025-01-21","cited_by_count":23,"area":null},{"id":"2503.00808","title":"Predictive Data Selection: The Data That Predicts Is the Data That Teaches","created":"2025-03-02","cited_by_count":21,"area":null},{"id":"2602.05400","title":"OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration","created":"2026-02-05","cited_by_count":21,"area":null},{"id":"2504.14194","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","created":"2025-04-19","cited_by_count":19,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2507.03253","title":"RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs","created":"2025-07-04","cited_by_count":17,"area":null},{"id":"2504.16511","title":"QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining","created":"2025-04-23","cited_by_count":16,"area":null},{"id":"2505.19051","title":"Efficient Data Selection at Scale via Influence Distillation","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2409.11378","title":"Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement","created":"2024-09-17","cited_by_count":13,"area":null},{"id":"2410.14208","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12,"area":null},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2410.15661","title":"Scalable Data Ablation Approximations for Language Models through Modular Training and Merging","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2410.08102","title":"Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration","created":"2024-10-10","cited_by_count":10,"area":null},{"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":"2502.00198","title":"Fairshare Data Pricing via Data Valuation for Large Language Models","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2505.12762","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","created":"2025-05-19","cited_by_count":8,"area":"alignment"},{"id":"2505.18513","title":"Enhancing Training Data Attribution with Representational Optimization","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2506.21545","title":"Data Efficacy for Language Model Training","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"area":"alignment"},{"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":"2507.16178","title":"LLM Data Selection and Utilization via Dynamic Bi-level Optimization","created":"2025-07-22","cited_by_count":7,"area":null},{"id":"2509.21359","title":"Influence Guided Context Selection for Effective Retrieval-Augmented Generation","created":"2025-09-21","cited_by_count":7,"area":"rag"},{"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":"2508.17677","title":"TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training","created":"2025-08-25","cited_by_count":6,"area":null},{"id":"2510.10023","title":"Skill-Targeted Adaptive Training","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2510.10681","title":"RePro: Training Language Models to Faithfully Recycle the Web for Pretraining","created":"2025-10-12","cited_by_count":6,"area":null},{"id":"2604.00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","created":"2026-04-01","cited_by_count":6,"area":"synth"},{"id":"2503.15573","title":"Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2507.09424","title":"DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models","created":"2025-07-12","cited_by_count":5,"area":null},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2501.02004","title":"General Information Metrics for Improving AI Model Training Efficiency","created":"2025-01-02","cited_by_count":4,"area":null},{"id":"2502.00955","title":"Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search","created":"2025-02-02","cited_by_count":4,"area":"agents"},{"id":"2502.05551","title":"FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy","created":"2025-02-08","cited_by_count":4,"area":null},{"id":"2605.18814","title":"How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2501.06708","title":"Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights","created":"2025-01-12","cited_by_count":3,"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":"2510.06048","title":"BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2512.13279","title":"AIR: Post-training Data Selection for Reasoning via Attention Head Influence","created":"2025-12-15","cited_by_count":3,"area":"lr"},{"id":"2604.08519","title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2606.11660","title":"Bergson: An Open Source Library for Data Attribution","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2504.05563","title":"Do Data Valuations Make Good Data Prices?","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2509.06524","title":"LAMDAS: LLM as an Implicit Classifier for Domain-specific Data Selection","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.15651","title":"Toward Efficient Influence Function: Dropout as a Compression Tool","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2601.02386","title":"Tree of Preferences for Diversified Recommendation","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2605.15675","title":"Interaction-Aware Influence Functions for Group Attribution","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.17849","title":"Generating Pretraining Tokens from Organic Data for Data-Bound Scaling","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.18650","title":"BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2608.24065","title":"Mechanistic Circuit Identification for Controllable Data Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2502.00761","title":"FIRE: Flexible Integration of Data Quality Ratings for Effective Pre-Training","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2505.12250","title":"Not All Documents Are What You Need for Extracting Instruction Tuning Data","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.16260","title":"Small-to-Large Generalization: Data Influences Models Consistently Across Scale","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.19893","title":"ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2604.11810","title":"GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.16197","title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2606.05165","title":"STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.18307","title":"DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.08646","title":"UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.24717","title":"DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2509.12581","title":"Exploring Training Data Attribution under Limited Access Constraints","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.15556","title":"Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2511.11648","title":"Lightweight Time Series Data Valuation on Time Series Foundation Models via In-Context Finetuning","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2512.21515","title":"Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.21759","title":"Influence Guided Sampling for Domain Adaptation of Text Retrievers","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.01207","title":"Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2602.03772","title":"UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2603.26138","title":"PruneFuse: Efficient Data Selection via Weight Pruning and Network Fusion","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.07739","title":"Efficient Dataset Selection for Continual Adaptation of Generative Recommenders","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.06166","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.17806","title":"AMO: Operator-level Adaptive Muon Orthogonalization","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.24077","title":"LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.07954","title":"Minibatch Selection for Language Models via Partition Matroid Constrained Gradient Matching","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.02266","title":"HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.00699","title":"Patterning in Practice: Debiasing Reward Models with Susceptibilities","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.32228","title":"CompassPlay: Rewarding the Proposer for Where It Moves the Solver","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32484","title":"Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32888","title":"Refreshing Less, Selecting Better: Reusing Stale Gradient Features for Efficient Influence-Based Data Selection","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32991","title":"What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34287","title":"ReScraper: Unified Scraping and Cleaning of Web Data for Effective LLM Pretraining","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2610.02593","title":"Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03432","title":"OptiSelect: How does the Optimizer Shape Data Curriculum?","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.17956","title":"Learning Distributions from Samples and Qualities","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}