SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models

• URL: http://arxiv.org/abs/2508.05015v1
• Date: Thu, 07 Aug 2025 03:50:48 GMT
• Title: SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models
• Authors: Dai Do, Manh Nguyen, Svetha Venkatesh, Hung Le,
• Abstract summary: Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
• Score: 51.74498855100541
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL). However, such methods require extensive data and compute, making them impractical for smaller models. Current approaches to curriculum learning or data selection are largely heuristic-driven or demand extensive computational resources, limiting their scalability and generalizability. We propose \textbf{SPaRFT}, a self-paced learning framework that enables efficient learning based on the capability of the model being trained through optimizing which data to use and when. First, we apply \emph{cluster-based data reduction} to partition training data by semantics and difficulty, extracting a compact yet diverse subset that reduces redundancy. Then, a \emph{multi-armed bandit} treats data clusters as arms, optimized to allocate training samples based on model current performance. Experiments across multiple reasoning benchmarks show that SPaRFT achieves comparable or better accuracy than state-of-the-art baselines while using up to \(100\times\) fewer samples. Ablation studies and analyses further highlight the importance of both data clustering and adaptive selection. Our results demonstrate that carefully curated, performance-driven training curricula can unlock strong reasoning abilities in LLMs with minimal resources.

Related papers

• PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery [11.20326903218271]
  Post-training techniques such as instruction tuning are commonly employed to recover model performance.<n>However, some irrelevant instructions may also introduce negative effects to model capacity recovery.<n>We propose textbfPost-training dtextbfAta textbfSelection method for textbfEfficient pruned large language model textbfRecovery (textbfPASER)
  arXiv  Detail & Related papers  (2025-02-18T07:11:08Z)
• Optimizing Pretraining Data Mixtures with LLM-Estimated Utility [52.08428597962423]
  Large Language Models improve with increasing amounts of high-quality training data.<n>We find token-counts outperform manual and learned mixes, indicating that simple approaches for dataset size and diversity are surprisingly effective.<n>We propose two complementary approaches: UtiliMax, which extends token-based $200s by incorporating utility estimates from reduced-scale ablations, achieving up to a 10.6x speedup over manual baselines; and Model Estimated Data Utility (MEDU), which leverages LLMs to estimate data utility from small samples, matching ablation-based performance while reducing computational requirements by $simx.
  arXiv  Detail & Related papers  (2025-01-20T21:10:22Z)
• Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
  Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data. We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
  arXiv  Detail & Related papers  (2024-10-22T06:43:28Z)
• Efficient Bias Mitigation Without Privileged Information [14.21628601482357]
  Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups. Existing bias mitigation methods that aim to address this issue often rely on group labels for training or validation. We propose Targeted Augmentations for Bias Mitigation (TAB), a framework that leverages the entire training history of a helper model to identify spurious samples. We show that TAB improves worst-group performance without any group information or model selection, outperforming existing methods while maintaining overall accuracy.
  arXiv  Detail & Related papers  (2024-09-26T09:56:13Z)
• Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review [50.78587571704713]
  Learn-Focus-Review (LFR) is a dynamic training approach that adapts to the model's learning progress.<n>LFR tracks the model's learning performance across data blocks (sequences of tokens) and prioritizes revisiting challenging regions of the dataset.<n>Compared to baseline models trained on the full datasets, LFR consistently achieved lower perplexity and higher accuracy.
  arXiv  Detail & Related papers  (2024-09-10T00:59:18Z)
• Self-training Large Language Models through Knowledge Detection [26.831873737733737]
  Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples. Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects.
  arXiv  Detail & Related papers  (2024-06-17T07:25:09Z)
• How to Train Data-Efficient LLMs [56.41105687693619]
  We study data-efficient approaches for pre-training language models (LLMs) We find that Ask-LLM and Density sampling are the best methods in their respective categories. In our comparison of 19 samplers, involving hundreds of evaluation tasks and pre-training runs, we find that Ask-LLM and Density are the best methods in their respective categories.
  arXiv  Detail & Related papers  (2024-02-15T02:27:57Z)
• Language models are weak learners [71.33837923104808]
  We show that prompt-based large language models can operate effectively as weak learners. We incorporate these models into a boosting approach, which can leverage the knowledge within the model to outperform traditional tree-based boosting. Results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
  arXiv  Detail & Related papers  (2023-06-25T02:39:19Z)
• INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models [40.54353850357839]
  We show how we can employ submodular optimization to select highly representative subsets of the training corpora. We show that the resulting models achieve up to $sim99%$ of the performance of the fully-trained models.
  arXiv  Detail & Related papers  (2023-05-11T09:24:41Z)
• RPLKG: Robust Prompt Learning with Knowledge Graph [14.531071492983767]
  multimodal pre-trained models like CLIP have significantly boosted performance in various experiments.<n>Existing methods often lack interpretability and impose high computational costs.<n>We propose Robust Prompt Learning with Knowledge Graph (RPLKG) to curate diverse, interpretable prompt sets automatically.
  arXiv  Detail & Related papers  (2023-04-21T08:22:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.