{"total":17,"rows":[{"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":"2508.11953","title":"Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models","created":"2025-08-16","cited_by_count":12,"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":"2406.15570","title":"DEM: Distribution Edited Model for Training with Mixed Data Distributions","created":"2024-06-21","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":"2502.09969","title":"Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data","created":"2025-02-14","cited_by_count":2,"area":null},{"id":"2507.12612","title":"Learning Task Mixtures from Task Affinities: A Probabilistic Graphical Model for Supervised Fine-Tuning","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2505.01523","title":"Subset Selection for Fine-Tuning: A Utility-Diversity Balanced Approach for Mathematical Domain Adaptation","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2511.19274","title":"Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2605.06900","title":"Accelerated Relax-and-Round for Concave Coverage Problems","created":"2026-05-07","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":"2607.01104","title":"CausalMix: Data Mixture as Causal Inference for Language Model Training","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.03655","title":"Decoupling Generation and Selection for Budget-Constrained Faithful Summarization","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.15935","title":"Token Distribution versus Data Volume: Domain Balancing in Multi-Domain Meeting Summarisation","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.36721","title":"CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39702","title":"A helps B while B hurts A: directed transfer in instruction-tuning mixture","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.14028","title":"Pick the Mixture, Not the Samples: Combinatorial Data Selection for LLMs","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}