{"total":71,"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":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2402.14526","title":"Balanced Data Sampling for Language Model Training with Clustering","created":"2024-02-22","cited_by_count":23,"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":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2502.06733","title":"Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining","created":"2025-02-10","cited_by_count":16,"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":"2411.14318","title":"Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2407.06380","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","created":"2024-07-08","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":"2503.01506","title":"SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity","created":"2025-03-03","cited_by_count":10,"area":null},{"id":"2510.25947","title":"Revisiting Multilingual Data Mixtures in Language Model Pretraining","created":"2025-10-29","cited_by_count":10,"area":null},{"id":"2601.21725","title":"Procedural Pretraining: Warming Up Language Models with Abstract Data","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2508.12116","title":"DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections","created":"2025-08-16","cited_by_count":9,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2505.16066","title":"Merge to Mix: Mixing Datasets via Model Merging","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2505.17293","title":"Graph Data Selection for Domain Adaptation: A Model-Free Approach","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2410.04579","title":"Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets","created":"2024-10-06","cited_by_count":6,"area":null},{"id":"2411.12986","title":"Training Bilingual LMs with Data Constraints in the Targeted Language","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2502.00270","title":"DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks","created":"2025-02-01","cited_by_count":6,"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":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2502.15950","title":"Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models","created":"2025-02-21","cited_by_count":5,"area":null},{"id":"2603.26164","title":"DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models","created":"2026-03-27","cited_by_count":5,"area":null},{"id":"2606.04261","title":"Can Generalist Agents Automate Data Curation?","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2502.16802","title":"Topic Over Source: The Key to Effective Data Mixing for Language Models Pre-training","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2504.13227","title":"DIDS: Domain Impact-aware Data Sampling for Large Language Model Training","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2505.20380","title":"GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2605.10770","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2411.11266","title":"VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs","created":"2024-11-18","cited_by_count":3,"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":"2504.00695","title":"ToReMi: Topic-Aware Data Reweighting for Dynamic Pre-Training Data Selection","created":"2025-04-01","cited_by_count":3,"area":null},{"id":"2505.00358","title":"R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training","created":"2025-05-01","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":"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":"2606.04401","title":"TANDEM: Bi-Level Data Mixture Optimization with Twin Networks","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2409.19800","title":"Differentially Private Bilevel Optimization","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2506.12966","title":"Assessing the Role of Data Quality in Training Bilingual Language Models","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2606.07597","title":"Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.11499","title":"Hubs or Fringes: Pretraining Data Selection via Web Graph Centrality","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2606.18663","title":"RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2608.14071","title":"Scaling Domain Data Repetition in LLM Pretraining","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2406.01477","title":"MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2410.10006","title":"TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2502.00340","title":"Unlocking Full Efficiency of Token Filtering in Large Language Model Training","created":"2025-02-01","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":"2512.10545","title":"XDoGE: Multilingual Data Reweighting to Enhance Language Inclusivity in LLMs","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2604.00001","title":"Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2606.14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2608.09093","title":"The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.10518","title":"BrainTaskonomy: Learning How to Pretrain and What to Transfer in fMRI Foundation Models","created":"2026-09-09","cited_by_count":1,"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":"2511.06913","title":"Sampling and Loss Weights in Multi-Domain Training","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2601.13588","title":"TREX: Tokenizer Regression for Optimal Data Mixture","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2605.15220","title":"Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time","created":"2026-05-13","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":"2608.11746","title":"Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.31102","title":"LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01573","title":"Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.09099","title":"Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.26160","title":"The Free-Recipe Limit: Every Recipe Effect Measures Which Premise of an Idealised Learner Broke","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.37255","title":"Loss-Guided Pretraining Data Selection for Time-Series Foundation Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00234","title":"Conflicting Supervision Moves Commitment, Not Capability: A 12.29{\\sigma} arrangement effect that is exactly zero under a convention-agnostic score","created":"2026-09-23","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":"2610.11548","title":"Conditional Transfer from Controlled Pretraining Mixtures to Code","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.19343","title":"Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}