{"total":43,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399,"area":null},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329,"area":null},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151,"area":null},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"area":null},{"id":"2205.12600","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","created":"2022-05-25","cited_by_count":34,"area":null},{"id":"2109.07437","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","created":"2021-09-15","cited_by_count":26,"area":null},{"id":"2207.11719","title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","created":"2022-07-24","cited_by_count":26,"area":null},{"id":"2206.04294","title":"FOAM: A Follower-aware Speaker Model For Vision-and-Language Navigation","created":"2022-06-09","cited_by_count":22,"area":null},{"id":"2109.02284","title":"Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training","created":"2021-09-06","cited_by_count":19,"area":null},{"id":"2203.06172","title":"Deep AutoAugment","created":"2022-03-11","cited_by_count":18,"area":null},{"id":"2108.11346","title":"Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral","created":"2021-08-25","cited_by_count":17,"area":null},{"id":"2102.07847","title":"Meta Back-translation","created":"2021-02-15","cited_by_count":16,"area":null},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2406.08811","title":"Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models","created":"2024-06-13","cited_by_count":16,"area":null},{"id":"2111.00056","title":"Generalized Data Weighting via Class-level Gradient Manipulation","created":"2021-10-29","cited_by_count":15,"area":null},{"id":"2101.10368","title":"Meta-Learning for Effective Multi-task and Multilingual Modelling","created":"2021-01-25","cited_by_count":13,"area":null},{"id":"2505.17895","title":"DataRater: Meta-Learned Dataset Curation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2311.11973","title":"Adaptive Training Distributions with Scalable Online Bilevel Optimization","created":"2023-11-20","cited_by_count":11,"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":"2410.02498","title":"Dynamic Gradient Alignment for Online Data Mixing","created":"2024-10-03","cited_by_count":10,"area":null},{"id":"2102.13549","title":"Gradient-guided Loss Masking for Neural Machine Translation","created":"2021-02-26","cited_by_count":8,"area":null},{"id":"2410.16710","title":"Influential Language Data Selection via Gradient Trajectory Pursuit","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","cited_by_count":6,"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":"2504.16277","title":"DataS^3: Dataset Subset Selection for Specialization","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2210.10293","title":"Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning","created":"2022-10-19","cited_by_count":5,"area":null},{"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":"2310.20121","title":"Ling-CL: Understanding NLP Models through Linguistic Curricula","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2511.16602","title":"Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2207.14386","title":"Efficient NLP Model Finetuning via Multistage Data Filtering","created":"2022-07-28","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":"2102.03275","title":"In-Loop Meta-Learning with Gradient-Alignment Reward","created":"2021-02-05","cited_by_count":1,"area":null},{"id":"2505.01665","title":"Adaptively Point-weighting Curriculum Learning","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2105.13464","title":"Training With Data Dependent Dynamic Learning Rates","created":"2021-05-27","cited_by_count":0,"area":null},{"id":"2112.00275","title":"Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2310.17386","title":"A Challenge in Reweighting Data with Bilevel Optimization","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2405.07769","title":"$\\alpha$VIL: Learning to Leverage Auxiliary Tasks for Multitask Learning","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2410.09642","title":"RepMatch: Quantifying Cross-Instance Similarities in Representation Space","created":"2024-10-12","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":"2601.22016","title":"TBDFiltering: Sample-Efficient Tree-Based Data Filtering","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.11615","title":"SkillRater: Untangling Capabilities in Multimodal Data","created":"2026-02-12","cited_by_count":0,"area":null}],"next_cursor":null}