arXiv:2608. 16926v1 Announce Type: new Abstract: Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while preserving model performance.
arXiv:2510. 16882v4 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks.
arXiv:2605. 21422v3 Announce Type: replace Abstract: As LLMs continue to scale up, improving training efficiency heavily relies on effective data utilization.
arXiv:2606. 19607v1 Announce Type: new Abstract: Preference-based post-training has become a central paradigm for aligning language models.
arXiv:2510. 06048v4 Announce Type: replace Abstract: Effective data selection is essential for pretraining large language models (LLMs), enhancing efficiency and improving generalization to downstream tasks.
arXiv:2606. 11189v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory.
arXiv:2607. 20465v1 Announce Type: new Abstract: The quality of training data fundamentally determines the capabilities of large language models (LLMs), yet no unified benchmark exists to measure how well LLMs, agents, and data-centric workflows actually prepare training data end to end.
arXiv:2606. 02521v1 Announce Type: new Abstract: One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization.
arXiv:2510. 26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems.
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
arXiv:2606. 07678v1 Announce Type: cross Abstract: Safety alignment for large language models relies on preference data, but current pipelines often train on large, redundant datasets.
arXiv:2602. 14696v2 Announce Type: replace Abstract: Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task.
One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step generators.