MAPLE: Metadata Augmented Private Language Evolution

• URL: http://arxiv.org/abs/2603.19258v1
• Date: Thu, 26 Feb 2026 14:18:36 GMT
• Title: MAPLE: Metadata Augmented Private Language Evolution
• Abstract summary: We propose Metadata Augmented Private Language Evolution (MAPLE) to ground the initial synthetic distribution in the target domain.<n> MAPLE achieves a significantly more favorable privacy-utility trade-off, converges faster, and drastically reduces API costs compared to previous PE methods.
• Score: 31.885554778844867
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While differentially private (DP) fine-tuning of large language models (LLMs) is a powerful tool, it is often computationally prohibitive or infeasible when state-of-the-art models are only accessible via proprietary APIs. In such settings, generating DP synthetic data has emerged as a crucial alternative, offering the added benefits of arbitrary reuse across downstream tasks and transparent exploratory data analysis without the opaque constraints of a model's parameter space. Private Evolution (PE) is a promising API-based framework for this goal; however, its performance critically depends on initialization. When the private data distribution deviates substantially from the foundation model's pre-training priors--particularly in highly specialized domains--PE frequently struggles to align with the target data, resulting in degraded utility, poor convergence, and inefficient API usage. To address this initialization bottleneck, we propose Metadata Augmented Private Language Evolution (MAPLE). MAPLE leverages differentially private tabular metadata extraction and in-context learning to effectively ground the initial synthetic distribution in the target domain. Extensive experiments on challenging, domain-specific text generation tasks demonstrate that MAPLE achieves a significantly more favorable privacy-utility trade-off, converges faster, and drastically reduces API costs compared to previous PE methods.

Related papers

• EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors [28.30281053018808]
  We introduce EPSVec, a lightweight alternative to existing private text generation methods.<n> EPSVec steers generation using *dataset vectors*--directions in activation space that capture the distributional gap between private data and public priors.<n>Our experiments demonstrate that EPSVec outperforms existing baselines in distributional alignment and downstream utility.
  arXiv  Detail & Related papers  (2026-01-31T00:04:08Z)
• Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only [70.43369087819332]
  Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models with human-annotated demonstrations.<n>We propose Self-Rewarding PPO, a novel fine-tuning method that leverages on-policy techniques to enhance generalization performance.
  arXiv  Detail & Related papers  (2025-10-24T02:02:13Z)
• Improving Noise Efficiency in Privacy-preserving Dataset Distillation [59.57846442477106]
  We introduce a novel framework that decouples sampling from optimization for better convergence and improves signal quality.<n>On CIFAR-10, our method achieves a textbf10.0% improvement with 50 images per class and textbf8.3% increase with just textbfone-fifth the distilled set size of previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-03T13:15:52Z)
• Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting [1.5595148909011116]
  Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs)<n>SFT often leads to a degradation of the model's general abilities, a phenomenon known as catastrophic forgetting.<n>We propose a novel and cost-effective SFT method that effectively mitigates catastrophic forgetting without requiring access to the original SFT data.
  arXiv  Detail & Related papers  (2025-06-11T06:23:50Z)
• PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs [39.108700932535754]
  Private Evolution (PE) algorithm generates Differential Privacy (DP) synthetic images using diffusion model APIs.<n>In practice, the few-shot private data challenge is particularly prevalent in specialized domains like healthcare and industry.<n>We propose a novel API-assisted algorithm, Private Contrastive Evolution (PCEvolve), which iteratively mines inherent inter-class contrastive relationships in few-shot private data.
  arXiv  Detail & Related papers  (2025-06-04T13:33:06Z)
• Personalized Language Models via Privacy-Preserving Evolutionary Model Merging [53.97323896430374]
  Personalization in language models aims to tailor model behavior to individual users or user groups.<n>We propose Privacy-Preserving Model Merging via Evolutionary Algorithms (PriME)<n>PriME employs gradient-free methods to directly optimize utility while reducing privacy risks.<n>Experiments on the LaMP benchmark show that PriME consistently outperforms a range of baselines, achieving up to a 45% improvement in task performance.
  arXiv  Detail & Related papers  (2025-03-23T09:46:07Z)
• Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models [2.3281513013731145]
  Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. Differential Privacy (DP) offers a solution to mitigate these risks, but introduces significant computational and performance trade-offs. We show that PEFT methods achieve comparable performance to standard fine-tuning while requiring fewer parameters and significantly reducing privacy leakage.
  arXiv  Detail & Related papers  (2024-11-24T13:17:36Z)
• Privacy-preserving datasets by capturing feature distributions with Conditional VAEs [0.11999555634662634]
  Conditional Variational Autoencoders (CVAEs) trained on feature vectors extracted from large pre-trained vision foundation models. Our method notably outperforms traditional approaches in both medical and natural image domains. Results underscore the potential of generative models to significantly impact deep learning applications in data-scarce and privacy-sensitive environments.
  arXiv  Detail & Related papers  (2024-08-01T15:26:24Z)
• Progressive Conservative Adaptation for Evolving Target Domains [76.9274842289221]
  Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain. Restoring and adapting to such target data results in escalating computational and resource consumption over time. We propose a simple yet effective approach, termed progressive conservative adaptation (PCAda)
  arXiv  Detail & Related papers  (2024-02-07T04:11:25Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [69.66654761324702]
  We propose a simple yet effective just-fine-tune-twice privacy mechanism to achieve SDP for large Transformer-based language models. Experiments show that our models achieve strong performance while staying robust to the canary insertion attack.
  arXiv  Detail & Related papers  (2022-04-15T22:36:55Z)

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.